© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134061
    Prev
    Next
    INDEX
    Explanations

    business

    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_1_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
    <0x0D>
    1.00
    ができる
    0.86
    t
    0.86
     to
    0.85
    يد
    0.84
    ய
    0.83
     at
    0.81
    を変
    0.81
    يو
    0.81
     papi
    0.79
    POSITIVE LOGITS
    و
    1.08
    ہ
    0.96
    and
    0.86
    )
    0.81
    KL
    0.79
    ne
    0.77
    
    0.77
    ली
    0.76
    issä
    0.75
    ),
    0.73
    Activations Density 0.005%

    No Known Activations