© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117115
    Prev
    Next
    INDEX
    Explanations

    ,

    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_27_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
    idikan
    0.34
     আরো
    0.33
    ઞ
    0.33
    ಾಗುತ್ತದೆ
    0.32
     首先
    0.32
     espon
    0.32
     capitalist
    0.32
     imediatamente
    0.32
    array
    0.32
     array
    0.31
    POSITIVE LOGITS
    ♡
    0.36
    재
    0.35
     MOU
    0.34
    ዝ
    0.33
     signing
    0.33
    Distribution
    0.31
     restarts
    0.31
    Re
    0.31
    เลือก
    0.31
    Spot
    0.30
    Activations Density 0.009%

    No Known Activations