© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207448
    Prev
    Next
    INDEX
    Explanations

    say "Parentheses"

    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
     diret
    0.47
     gson
    0.46
    状态
    0.44
    атр
    0.43
     directs
    0.43
     Emil
    0.42
     screwing
    0.41
    ‹
    0.39
     डायरे
    0.38
     noise
    0.38
    POSITIVE LOGITS
    HE
    0.59
    hew
    0.59
    ヘ
    0.53
    <0x88>
    0.52
    hé
    0.52
     хе
    0.51
    хе
    0.51
    Hew
    0.49
     Hew
    0.49
    henge
    0.49
    Activations Density 0.000%

    No Known Activations