© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261121
    Prev
    Next
    INDEX
    Explanations

    Toba supervolcano eruptions

    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_5_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
    이다
    1.13
    них
    1.12
    ви
    1.09
    у
    1.09
     as
    1.06
    ’
    1.06
    <0x0D>
    1.05
    1.05
    I
    1.05
     with
    1.02
    POSITIVE LOGITS
    ك
    1.60
    the
    1.36
    ح
    1.22
    in
    1.18
    f
    1.08
    il
    1.07
    os
    1.07
    se
    1.05
    k
    1.04
    typen
    1.03
    Activations Density 0.000%

    No Known Activations