© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31487
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers

    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_31_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
     ±
    0.39
    勲
    0.37
    Cases
    0.36
    拔
    0.36
    ajj
    0.36
    าว
    0.35
     tow
    0.35
    did
    0.35
    ღ
    0.34
    卤
    0.34
    POSITIVE LOGITS
     MISS
    0.44
     binding
    0.40
     isbn
    0.40
     bindings
    0.40
    isbn
    0.39
     Penguin
    0.39
     bangunan
    0.38
     jury
    0.38
     strerror
    0.38
     tying
    0.38
    Activations Density 0.000%

    No Known Activations