© 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. 39422
    Prev
    Next
    INDEX
    Explanations

    backstab, backwash, backup, backwater, back extensions

    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
    ле
    1.32
    р
    0.88
    т
    0.86
    ي
    0.84
    سم
    0.83
    ли
    0.79
    ча
    0.79
    ’
    0.79
     fluctu
    0.75
     slanted
    0.75
    POSITIVE LOGITS
    3
    0.75
    ని
    0.70
     as
    0.69
    0.67
    ുള്ള
    0.66
     world
    0.64
    daki
    0.63
    Current
    0.62
    Client
    0.61
    ON
    0.61
    Activations Density 0.014%

    No Known Activations