© 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. 49475
    Prev
    Next
    INDEX
    Explanations

    paid, extra, fees

    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
     Cadastro
    0.41
     விருப்ப
    0.40
    Cadastro
    0.40
    浸
    0.39
     ऑप्शन
    0.38
    涂
    0.37
     opções
    0.37
    िवेदी
    0.37
     vaso
    0.36
     purg
    0.36
    POSITIVE LOGITS
    âche
    0.44
    _.
    0.40
     winners
    0.37
     lijkt
    0.37
     meh
    0.36
    nich
    0.36
     واقف
    0.36
     Winners
    0.36
    ns
    0.35
    ihan
    0.35
    Activations Density 0.004%

    No Known Activations