© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87854
    Prev
    Next
    INDEX
    Explanations

    file extension type

    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_23_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
     ਉਹ
    0.42
     conveys
    0.42
     impenetr
    0.41
    като
    0.41
    डेंगू
    0.40
    ϙ
    0.40
    กร
    0.38
     fluffy
    0.36
     macarons
    0.36
    ecção
    0.35
    POSITIVE LOGITS
    anske
    0.44
    絲
    0.43
     réc
    0.42
     arit
    0.39
     Hora
    0.37
    矣
    0.37
     fisk
    0.36
     Qc
    0.36
     tyr
    0.36
     csal
    0.36
    Activations Density 0.000%

    No Known Activations