© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220738
    Prev
    Next
    INDEX
    Explanations

    opens possibilities

    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_10_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
    \
    0.89
    1
    0.86
    <
    0.80
    "
    0.76
    ",
    0.71
    క
    0.71
    لا
    0.70
     as
    0.68
     Organizations
    0.68
    فر
    0.66
    POSITIVE LOGITS
     Бен
    0.94
     Ко
    0.87
     BAFTA
    0.85
     ಕೊಟ್ಟ
    0.84
     Ке
    0.82
    kta
    0.82
    ljenje
    0.82
     Бар
    0.81
     සිදු
    0.81
    Rightarrow
    0.80
    Activations Density 0.003%

    No Known Activations