© 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. 45637
    Prev
    Next
    INDEX
    Explanations

    lived in a

    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
    転職
    0.39
     Gep
    0.39
    楲
    0.39
    majority
    0.38
     lt
    0.37
    continental
    0.37
     Japan
    0.37
    ிட்டு
    0.37
    ub
    0.36
     забезпечення
    0.36
    POSITIVE LOGITS
     /\.
    0.42
    Diagnostic
    0.41
     важных
    0.41
    NonUser
    0.41
    लेश्वर
    0.41
    కం
    0.40
    ALS
    0.40
     සඳ
    0.40
    LOGIN
    0.40
     valam
    0.39
    Activations Density 0.001%

    No Known Activations