© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90748
    Prev
    Next
    INDEX
    Explanations

    math operations

    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_60_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
    ("__
    0.62
    فی
    0.58
    ((*
    0.56
    ((\
    0.55
    ("_
    0.54
    (($
    0.54
    (((
    0.53
    ("[
    0.52
    حی
    0.52
    ("(
    0.52
    POSITIVE LOGITS
    _
    0.83
    _{
    0.82
    _{\
    0.53
     For
    0.47
     Positive
    0.45
     positive
    0.45
     K
    0.44
    For
    0.44
     for
    0.43
     Private
    0.43
    Activations Density 0.001%

    No Known Activations