© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205161
    Prev
    Next
    INDEX
    Explanations

    reported words and numbers

    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_6_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
    t
    1.77
    ב
    1.72
    т
    1.49
    b
    1.35
    c
    1.31
    ת
    1.30
    ت
    1.30
    ম
    1.23
    d
    1.21
    д
    1.18
    POSITIVE LOGITS
     in
    0.96
     في
    0.85
    EB
    0.77
    OSE
    0.74
    (
    0.74
    I
    0.72
    在
    0.71
     =)
    0.71
     ===
    0.71
    EIN
    0.68
    Activations Density 0.001%

    No Known Activations