© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89299
    Prev
    Next
    INDEX
    Explanations

    numbers followed by date

    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
     to
    0.86
    ות
    0.82
    ک
    0.82
    ?
    0.73
    на
    0.71
    ہ
    0.71
    ৭
    0.70
    रा
    0.69
     serão
    0.67
    ８
    0.66
    POSITIVE LOGITS
    ib
    0.73
    achlor
    0.65
    us
    0.64
    one
    0.63
    彷
    0.61
    ir
    0.59
    probably
    0.58
    Songs
    0.58
    unat
    0.57
    ButtonBar
    0.55
    Activations Density 0.010%

    No Known Activations