© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143054
    Prev
    Next
    INDEX
    Explanations

    svc or Pt followed by code/text

    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_0_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
    n
    1.93
    to
    1.69
     to
    1.55
    ی
    1.48
    મ
    1.47
    ı
    1.45
    ε
    1.45
    ર
    1.45
    is
    1.43
    of
    1.43
    POSITIVE LOGITS
    Config
    1.31
    0
    1.30
    Code
    1.27
    Header
    1.21
    Active
    1.20
    Date
    1.18
    Current
    1.17
    Message
    1.16
    Default
    1.16
    padă
    1.14
    Activations Density 0.000%

    No Known Activations