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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 656
    Prev
    Next
    INDEX
    Explanations

    high-value words in context, with no central theme

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    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
    hoeddwyd
    -0.51
     Baillargeon
    -0.47
    упо
    -0.47
    styleType
    -0.47
     harp
    -0.44
    PreferredItem
    -0.44
     Spot
    -0.44
    Factor
    -0.43
    braith
    -0.43
    rook
    -0.43
    POSITIVE LOGITS
     Pons
    0.76
    Ops
    0.75
     Lins
    0.73
    tims
    0.72
     ops
    0.72
    Meds
    0.70
     Cans
    0.69
     Ops
    0.69
     Pins
    0.69
    tvguidetime
    0.69
    Activations Density 11.694%

    No Known Activations