© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160286
    Prev
    Next
    INDEX
    Explanations

    Runes

    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_2_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
    t
    1.63
    я
    1.22
    ק
    1.06
    на
    1.04
    ম
    1.02
    ка
    0.98
    も
    0.98
    й
    0.91
    在
    0.90
    мы
    0.90
    POSITIVE LOGITS
    as
    1.06
    ERICK
    0.84
    čené
    0.83
    il
    0.80
    el
    0.74
    olni
    0.73
     disastrous
    0.72
    리로
    0.72
    다라고
    0.72
    or
    0.68
    Activations Density 0.000%

    No Known Activations