© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9120
    Prev
    Next
    INDEX
    Explanations

    hyphenated words starting with "cut" or "kick" and the verb "pull it" or "head".

    oai_token-act-pair · gemini-2.0-flash

    something cut off/kicked off

    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
     off
    -2.94
     Off
    -2.55
    Off
    -2.53
    off
    -2.45
     OFF
    -2.20
    OFF
    -2.17
     offs
    -1.91
    offs
    -1.89
    オフ
    -1.63
     オフ
    -1.31
    POSITIVE LOGITS
    InitVars
    0.61
     يتيمه
    0.60
    Rohy
    0.59
    tagHelperRunner
    0.57
    رشف
    0.50
    fjspx
    0.48
    pasti
    0.46
     estekak
    0.45
     öz
    0.43
     ролях
    0.43
    Activations Density 1.057%

    No Known Activations