© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14174
    Prev
    Next
    INDEX
    Explanations

    code related to number of updates

    oai_token-act-pair · gemini-2.0-flash

    Code dealing with updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    PullParser
    -0.69
    '},
    -0.64
     cref
    -0.56
    )++;
    -0.56
    aryn
    -0.54
    Xna
    -0.52
    '],
    -0.52
    oula
    -0.50
    
    -0.50
    BASEPATH
    -0.50
    POSITIVE LOGITS
     fieldNum
    0.67
    elemField
    0.63
     متعلقه
    0.59
     Exactos
    0.58
    🦵
    0.56
     sério
    0.51
    forhold
    0.50
     soñar
    0.50
    IsInitialized
    0.50
     argc
    0.49
    Activations Density 1.408%

    No Known Activations