© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194505
    Prev
    Next
    INDEX
    Explanations

    file suffixes and punctuation

    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_9_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
     that
    0.85
     romanos
    0.78
    。
    0.75
     augmenter
    0.71
     advocating
    0.70
     interact
    0.70
     invade
    0.69
     prodigious
    0.69
     isotopes
    0.68
     conceitos
    0.68
    POSITIVE LOGITS
    isiä
    0.85
    u
    0.79
    is
    0.79
    ा
    0.79
    的
    0.78
    a
    0.77
    nik
    0.74
    là
    0.73
    лық
    0.73
    lk
    0.72
    Activations Density 0.001%

    No Known Activations