© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151179
    Prev
    Next
    INDEX
    Explanations

    code components

    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_59_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
    ad
    1.42
    ads
    1.29
    ids
    1.16
    ds
    1.16
    דים
    1.16
    eds
    1.15
    드
    1.15
    id
    1.13
    드를
    1.11
    od
    1.09
    POSITIVE LOGITS
    iflix
    0.36
    luft
    0.34
    Alabama
    0.34
    moon
    0.33
    میان
    0.33
    Angleterre
    0.33
    ualan
    0.33
    allyl
    0.33
     lymphomas
    0.33
    istiques
    0.32
    Activations Density 0.031%

    No Known Activations