© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3658
    Prev
    Next
    INDEX
    Explanations

    the word "indirect", and sometimes words related to teaching or joints

    oai_token-act-pair · gemini-2.0-flash

    indirect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    er
    -0.79
    s
    -0.65
    </b>
    -0.63
    </td>
    -0.62
    <i>
    -0.57
    ?
    -0.57
    re
    -0.56
    ers
    -0.53
    ity
    -0.53
    e
    -0.52
    POSITIVE LOGITS
    <bos>
    0.96
     Monfieur
    0.88
     مرئيه
    0.84
     RIPRODUZIONE
    0.83
    Билгалдахарш
    0.80
     himſelf
    0.78
     myſelf
    0.78
     leaſt
    0.77
     nôtre
    0.76
     ब्रेकडाउन
    0.75
    Activations Density 2.014%

    No Known Activations