© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148981
    Prev
    Next
    INDEX
    Explanations

    start/end node or goal in paths

    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
     begele
    0.41
    ância
    0.39
    妷
    0.39
     Bans
    0.38
    攔
    0.38
     белән
    0.37
     बघेल
    0.36
     aparelho
    0.36
     खाते
    0.36
     sesiones
    0.36
    POSITIVE LOGITS
     adap
    0.46
     regulators
    0.43
    lava
    0.42
    COPY
    0.41
    poor
    0.40
     bioavailability
    0.40
    Myc
    0.39
     conserve
    0.38
     regulator
    0.38
    먀
    0.38
    Activations Density 0.003%

    No Known Activations