© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87156
    Prev
    Next
    INDEX
    Explanations

    batgirl, batocera, batwa, bat-computer, batson, batgpt, batna

    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_3_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
     موقف
    0.60
    ၣ်
    0.58
     لے
    0.57
    詑
    0.57
    اریخ
    0.56
     значення
    0.55
    planilla
    0.54
     চিকিৎ
    0.53
     വിൽപ്പന
    0.53
     Chủ
    0.53
    POSITIVE LOGITS
    </h2>
    0.91
    </u>
    0.88
    ur
    0.88
    .
    0.87
    ;
    0.86
    <0x0D>
    0.85
    o
    0.85
    </b>
    0.84
    :
    0.82
    स
    0.80
    Activations Density 0.000%

    No Known Activations