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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14332
    Prev
    Next
    INDEX
    Explanations

    words that express avoiding something either physically by moving or metaphorically

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    webElement
    -0.68
    /=
    -0.56
    اریخ
    -0.56
    ściej
    -0.55
    🏾
    -0.54
     refresh
    -0.54
     Ball
    -0.53
    новниш
    -0.52
    TestingModule
    -0.52
    ]!='
    -0.52
    POSITIVE LOGITS
     jäm
    0.51
     même
    0.48
    Personensuche
    0.48
     hoffe
    0.47
     '-':
    0.45
     tuong
    0.45
    __*/
    0.45
    汰
    0.44
     podob
    0.43
     resourceCulture
    0.42
    Activations Density 1.621%

    No Known Activations