© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18018
    Prev
    Next
    INDEX
    Explanations

    <meta name="viewport"

    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_15_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
    ال
    0.55
     типу
    0.54
    h
    0.50
    v
    0.50
    崤
    0.49
    襁
    0.49
    Фі
    0.49
    ge
    0.49
    Hash
    0.47
    z
    0.47
    POSITIVE LOGITS
     suboptimal
    0.55
     bartender
    0.54
     STUDENT
    0.54
    JECT
    0.53
     Student
    0.53
    clementine
    0.53
     Librarian
    0.52
     Prisoner
    0.52
     ImageTk
    0.51
     knockdown
    0.51
    Activations Density 0.002%

    No Known Activations