© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112651
    Prev
    Next
    INDEX
    Explanations

    turn up the volume

    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
     to
    1.18
    기
    1.16
    什么
    1.12
    나
    1.08
    ן
    1.04
     때문에
    1.03
     at
    1.01
    '&
    1.01
     gums
    1.00
     subsidiaries
    0.98
    POSITIVE LOGITS
    p
    1.52
    2
    1.46
    l
    1.44
    W
    1.40
    ed
    1.38
    s
    1.36
    as
    1.30
    she
    1.25
    with
    1.20
    i
    1.18
    Activations Density 0.000%

    No Known Activations