© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104066
    Prev
    Next
    INDEX
    Explanations

    characterised by / exists

    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_1_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
     for
    1.81
    ur
    1.29
    us
    1.17
    is
    1.12
    ↵
    1.05
    u
    1.05
    ר
    1.02
    ↵↵
    1.01
    en
    1.01
     from
    0.95
    POSITIVE LOGITS
    ков
    1.06
    ২
    1.05
    ━
    0.98
     in
    0.96
    с
    0.93
     янва
    0.86
    :#
    0.85
    し
    0.84
    soever
    0.84
     hassles
    0.84
    Activations Density 0.000%

    No Known Activations