© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157699
    Prev
    Next
    INDEX
    Explanations

    adhesives

    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
    보면
    0.99
    !=
    0.98
    țile
    0.95
    ться
    0.94
    '}}
    0.93
    _
    0.92
    ى
    0.89
    šću
    0.87
     The
    0.85
     aprovechar
    0.84
    POSITIVE LOGITS
    s
    1.48
    ry
    1.21
    ع
    1.19
    2
    1.16
    ll
    1.09
    ps
    0.98
    da
    0.98
    ss
    0.98
    sp
    0.98
    ם
    0.97
    Activations Density 0.000%

    No Known Activations