© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163218
    Prev
    Next
    INDEX
    Explanations

    ' and `t` or 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
    建立了
    0.04
    Spark
    0.04
     SIE
    0.04
    츰
    0.04
    庆
    0.04
    supp
    0.04
    ijom
    0.04
    ḧ
    0.04
    amię
    0.04
    ቸው
    0.04
    POSITIVE LOGITS
    Ao
    0.05
     eyes
    0.05
     groupings
    0.05
     umano
    0.05
     ao
    0.04
     troughs
    0.04
     sausages
    0.04
     instructions
    0.04
     humans
    0.04
     mensch
    0.04
    Activations Density 0.000%

    No Known Activations