© 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. 86813
    Prev
    Next
    INDEX
    Explanations

    no cost

    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
    0.82
    c
    0.79
     It
    0.65
    gl
    0.63
    ，
    0.61
     or
    0.60
     We
    0.59
    лё
    0.59
    h
    0.58
    し
    0.58
    POSITIVE LOGITS
     créer
    0.69
    :
    0.68
     сеть
    0.68
     salle
    0.66
     naam
    0.66
     гражда
    0.63
     сете
    0.63
    et
    0.62
     каждый
    0.62
     soupe
    0.62
    Activations Density 0.000%

    No Known Activations