© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219243
    Prev
    Next
    INDEX
    Explanations

    before or after 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_31_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
    ρω
    0.33
    Ur
    0.31
    ❷
    0.31
    Using
    0.30
    ISH
    0.29
     وبا
    0.29
    ])):
    0.29
    を使用して
    0.29
     incumb
    0.29
    :][
    0.28
    POSITIVE LOGITS
    cret
    0.34
    atine
    0.34
     Vort
    0.34
     असंभव
    0.34
    了一条
    0.31
    opathie
    0.31
     before
    0.31
    unteers
    0.30
     Diploma
    0.30
    terase
    0.30
    Activations Density 0.009%

    No Known Activations