© 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. 23572
    Prev
    Next
    INDEX
    Explanations

    places and venues

    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
     parametr
    0.41
     knowingly
    0.40
    తీ
    0.39
    coverageStat
    0.36
    -'].
    0.36
     Alert
    0.35
     कड़ी
    0.35
     VCO
    0.35
     Spending
    0.35
     Nordstrom
    0.35
    POSITIVE LOGITS
    <unused509>
    0.41
    гор
    0.39
    Dennis
    0.38
    ianthus
    0.37
     Bij
    0.37
     બન
    0.37
    bathing
    0.37
    彠
    0.37
    𓏧
    0.37
     plasmas
    0.36
    Activations Density 0.004%

    No Known Activations