© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61677
    Prev
    Next
    INDEX
    Explanations

    Styrofoam

    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_59_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
    st
    0.55
    g
    0.48
    m
    0.47
    an
    0.46
    son
    0.43
    labor
    0.42
    internal
    0.41
    ide
    0.40
    statements
    0.39
    gur
    0.38
    POSITIVE LOGITS
     ר
    0.50
     rt
    0.47
     esf
    0.47
     Ou
    0.46
     расту
    0.46
     rowspan
    0.45
     rin
    0.44
     rojo
    0.44
     Pad
    0.44
     Pra
    0.43
    Activations Density 0.000%

    No Known Activations