© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257860
    Prev
    Next
    INDEX
    Explanations

    perform tasks that

    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_22_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
    Gosudarstvennyj
    0.50
    zó
    0.48
    Tanggal
    0.48
    ()*
    0.48
    ⅾ
    0.46
    önet
    0.46
     tarihi
    0.46
    ził
    0.46
    zył
    0.45
     బ్రిటిష్
    0.45
    POSITIVE LOGITS
     employers
    0.47
    .
    0.45
     associating
    0.45
     Award
    0.44
     hộ
    0.43
    وران
    0.43
     lumped
    0.43
     unintentional
    0.42
     applying
    0.42
     importers
    0.42
    Activations Density 0.000%

    No Known Activations