© 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. 41665
    Prev
    Next
    INDEX
    Explanations

    underlayment / coverment

    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
    ן
    1.10
    ก
    0.86
    軞
    0.79
    芢
    0.72
    㐰
    0.71
    ᵚ
    0.71
    럏
    0.70
    ก่อน
    0.70
     remport
    0.70
    䊀
    0.70
    POSITIVE LOGITS
    ↵
    1.06
    ;
    0.89
    ana
    0.74
    =
    0.74
    -
    0.73
    :
    0.73
    are
    0.72
    </h3>
    0.71
    ai
    0.70
    ching
    0.69
    Activations Density 0.002%

    No Known Activations