© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    javascript require statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ín
    0.42
    ="|
    0.42
    <0x98>
    0.38
    </li>
    0.35
    =",
    0.34
    SpawnEntry
    0.34
    </h6>
    0.33
    শনার
    0.33
     Hijo
    0.32
     közül
    0.32
    POSITIVE LOGITS
    elijk
    0.45
    पूर
    0.42
    élect
    0.42
    ба
    0.42
    権利
    0.41
     زید
    0.40
    パ
    0.40
    را
    0.40
    adresse
    0.40
    шие
    0.39
    Activations Density 0.003%

    No Known Activations