© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253500
    Prev
    Next
    INDEX
    Explanations

    product images

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Pul
    0.42
    we
    0.36
    row
    0.36
    rows
    0.36
     nostru
    0.35
    全体
    0.35
    行
    0.35
    ᑉ
    0.35
     الوز
    0.34
     Dominicana
    0.34
    POSITIVE LOGITS
     seta
    0.45
     चाइल्ड
    0.40
     set
    0.40
     Child
    0.38
     Set
    0.38
     Stat
    0.38
    -[
    0.38
    Set
    0.37
     CHILD
    0.37
    Stat
    0.36
    Activations Density 0.000%

    No Known Activations