© 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. 61842
    Prev
    Next
    INDEX
    Explanations

    quote

    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
    ু
    1.24
    ي
    1.20
    an
    1.19
    та
    1.16
    ان
    1.08
     что
    1.05
    м
    1.03
    ુ
    1.03
    m
    1.02
    ಾ
    1.01
    POSITIVE LOGITS
     as
    1.32
     are
    0.91
    grave
    0.80
     have
    0.76
     revolt
    0.76
     (
    0.71
    gain
    0.68
    گاہ
    0.66
    abouts
    0.65
    !
    0.65
    Activations Density 0.002%

    No Known Activations