© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148843
    Prev
    Next
    INDEX
    Explanations

    itemize or list

    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_23_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
     loves
    0.49
    蹺
    0.46
     সামনের
    0.44
    illustration
    0.40
     love
    0.40
    ದು
    0.39
    ws
    0.39
    ิร์
    0.39
    どうぞ
    0.39
    mj
    0.38
    POSITIVE LOGITS
     corretamente
    0.49
     quadrado
    0.43
     medida
    0.42
    ULTY
    0.41
     ổn
    0.40
    '`--'`--
    0.40
     Measure
    0.39
     fail
    0.39
     ủy
    0.39
     rotacao
    0.38
    Activations Density 0.000%

    No Known Activations