© 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. 134327
    Prev
    Next
    INDEX
    Explanations

    hydrothermal vents

    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
    ش
    1.69
    t
    1.63
    一
    1.36
    The
    1.33
    m
    1.29
    മ
    1.28
    ע
    1.27
    ین
    1.26
    נ
    1.26
    ع
    1.24
    POSITIVE LOGITS
    ab
    1.16
     (
    1.16
     fø
    1.02
     be
    1.01
     haven
    0.96
     expenditure
    0.95
     obtuse
    0.93
     gratu
    0.92
    he
    0.91
     experience
    0.91
    Activations Density 0.001%

    No Known Activations