© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20276
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     compressibility
    0.45
    ற்றம்
    0.38
     deportation
    0.38
     build
    0.37
    geno
    0.37
     ipt
    0.37
    /
    0.36
     MIMO
    0.36
     bagi
    0.36
     ’
    0.35
    POSITIVE LOGITS
    ضل
    0.42
    uuid
    0.35
    derived
    0.35
    Peer
    0.35
    USER
    0.35
     Trouvez
    0.34
    然后在
    0.34
    Log
    0.34
    already
    0.34
    Dice
    0.34
    Activations Density 0.000%

    No Known Activations