© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159189
    Prev
    Next
    INDEX
    Explanations

    droop and drop

    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
    time
    1.63
    ta
    1.53
    to
    1.41
    as
    1.34
    p
    1.31
    ts
    1.22
    thesis
    1.14
    да
    1.12
    set
    1.09
    ier
    1.09
    POSITIVE LOGITS
    \
    1.41
    َ
    1.41
    ми
    1.26
    ший
    1.23
    ۵
    1.16
    ));
    1.15
    ции
    1.14
    ри
    1.13
    )
    1.12
    шой
    1.09
    Activations Density 0.000%

    No Known Activations