© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1976
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

    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_39_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
    Netflix
    0.47
    Vin
    0.41
    Mind
    0.41
    的話
    0.41
     Teens
    0.40
    パ
    0.40
     streaming
    0.40
    Align
    0.39
     Netflix
    0.38
     teenagers
    0.37
    POSITIVE LOGITS
    larından
    0.45
    =\$
    0.44
     ..."
    0.42
     trasera
    0.42
    िखर
    0.41
     मल
    0.40
    )²
    0.40
    сми
    0.40
    ]==
    0.40
    )==
    0.40
    Activations Density 0.076%

    No Known Activations