© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2241
    Prev
    Next
    INDEX
    Explanations

    words related to switches, levers, and mechanical linkages

    oai_token-act-pair · gemini-2.0-flash

    mechanical systems

    np_max-act-logits · gemini-2.0-flash

    say "mechanical verbs" Method used: 2 — tokens are action words describing mechanical operation — say "mechanical verbs"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igshid
    -0.52
     TextInputType
    -0.49
    FormState
    -0.45
     Lloyd
    -0.44
    Loop
    -0.44
    fe
    -0.43
     dikel
    -0.43
    Jereo
    -0.43
     loop
    -0.43
     Bo
    -0.43
    POSITIVE LOGITS
    +#+
    0.69
    aarrggbb
    0.57
     autorytatywna
    0.57
    ,:,
    0.57
    AnchorStyles
    0.57
    tagHelperRunner
    0.56
    Bibliograf
    0.56
    ]<=
    0.55
    Conscious
    0.54
    acamata
    0.54
    Activations Density 3.246%

    No Known Activations