© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36300
    Prev
    Next
    INDEX
    Explanations

    pickle spear

    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
    B
    0.80
     permet
    0.63
    T
    0.63
    U
    0.62
    מוד
    0.59
    спи
    0.57
    או
    0.56
    V
    0.56
    Y
    0.56
    to
    0.55
    POSITIVE LOGITS
    il
    1.11
    ac
    0.89
    ap
    0.77
    el
    0.74
    ل
    0.74
    are
    0.71
    ah
    0.69
    ある
    0.68
    aj
    0.68
    im
    0.67
    Activations Density 0.002%

    No Known Activations