© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200070
    Prev
    Next
    INDEX
    Explanations

    config option builder

    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
    स
    0.41
    S
    0.40
    𝑺
    0.39
    F
    0.39
    int
    0.38
    T
    0.38
    ä
    0.37
    f
    0.36
    AZ
    0.35
    س
    0.35
    POSITIVE LOGITS
    કિસ્તા
    0.38
     Pursuit
    0.38
     압
    0.36
     refusing
    0.36
     pursued
    0.35
     interdit
    0.35
     pursuit
    0.34
     لیاقت
    0.34
     chiede
    0.33
     onderste
    0.33
    Activations Density 0.000%

    No Known Activations