© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3423
    Prev
    Next
    INDEX
    Explanations

    html code blocks

    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_40_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
    荇
    0.35
     impoverished
    0.32
    Helen
    0.32
     работо
    0.31
    诙
    0.31
    Damage
    0.31
    곸
    0.31
    LinkLabel
    0.31
    沢
    0.30
    菣
    0.30
    POSITIVE LOGITS
    ռ
    0.32
    adies
    0.31
     걸
    0.30
    fdPar
    0.30
    udent
    0.30
    ৬০
    0.30
     take
    0.30
     Description
    0.30
    emb
    0.30
    -*
    0.30
    Activations Density 0.004%

    No Known Activations