© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50090
    Prev
    Next
    INDEX
    Explanations

    vector operations

    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_55_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
    title
    0.43
    tr
    0.42
    mrow
    0.39
    req
    0.39
    CJK
    0.39
    Tr
    0.38
    Ř
    0.38
    lama
    0.37
    صاب
    0.37
    yoga
    0.36
    POSITIVE LOGITS
     per
    0.40
     peritone
    0.40
     downstream
    0.39
    >&
    0.37
    endente
    0.36
     normalizing
    0.35
    .>
    0.35
    理想
    0.35
    単純
    0.35
     inwon
    0.34
    Activations Density 0.000%

    No Known Activations