© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203402
    Prev
    Next
    INDEX
    Explanations

    soufflé

    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_12_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
    𝙋
    0.40
    ப்பட்டது
    0.38
    Florence
    0.38
    вары
    0.37
    𝓌
    0.37
    RegistrationBean
    0.36
     Pudding
    0.36
    soon
    0.35
    turns
    0.35
    vita
    0.35
    POSITIVE LOGITS
     relinquished
    0.41
    '
    0.40
     quizz
    0.39
     rattled
    0.36
     allocated
    0.35
     scaled
    0.35
     negated
    0.35
     hypothesized
    0.35
     circulated
    0.34
     had
    0.34
    Activations Density 0.001%

    No Known Activations