© 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. 126191
    Prev
    Next
    INDEX
    Explanations

    pointer;

    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
    䬲
    0.65
     assurer
    0.64
    ꯋ
    0.64
     دليل
    0.63
    リビング
    0.61
    )’
    0.60
    렜
    0.59
     imidazol
    0.58
     সময়ই
    0.57
    噰
    0.57
    POSITIVE LOGITS
    m
    0.95
    g
    0.73
    ac
    0.72
    3
    0.72
    ни
    0.69
    ки
    0.68
    <0x80>
    0.67
    4
    0.66
    ap
    0.65
    im
    0.65
    Activations Density 0.001%

    No Known Activations