© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133666
    Prev
    Next
    INDEX
    Explanations

    selflessness inspire

    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_6_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
    1.22
    )،
    0.82
    ะ
    0.81
    s
    0.75
    ari
    0.74
    ە
    0.72
    ),
    0.70
     verdicts
    0.70
    ֔
    0.70
    </h2>
    0.69
    POSITIVE LOGITS
    '
    0.96
    Α
    0.82
    freund
    0.82
     Noch
    0.78
    Р
    0.75
    Preis
    0.73
     může
    0.73
    vertrag
    0.73
     těch
    0.73
     realizará
    0.72
    Activations Density 0.000%

    No Known Activations