© 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. 103702
    Prev
    Next
    INDEX
    Explanations

    mean calculation

    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
    p
    1.20
    ל
    1.18
    A
    1.09
    of
    1.08
    л
    1.08
    v
    1.05
     in
    1.04
    st
    1.02
    ד
    1.02
    </h3>
    1.01
    POSITIVE LOGITS
     vattum
    1.18
    <0x80>
    1.11
     mastect
    1.06
     núcle
    1.05
    ᱐
    1.02
     возра
    0.99
     equilíbrio
    0.98
     repellat
    0.98
    行った
    0.98
     khắc
    0.96
    Activations Density 0.005%

    No Known Activations