© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166572
    Prev
    Next
    INDEX
    Explanations

    UI components and vocabulary

    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_31_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
    ኵ
    0.36
     hlad
    0.34
    槛
    0.34
    give
    0.33
    timeout
    0.33
     estando
    0.33
     threshold
    0.32
    iders
    0.32
    ഽ
    0.32
    short
    0.31
    POSITIVE LOGITS
     racked
    0.34
     UIButton
    0.33
     slotted
    0.32
     حاجه
    0.32
     Forth
    0.31
     injected
    0.30
     Minerals
    0.30
     Helene
    0.30
     papel
    0.30
     sns
    0.30
    Activations Density 0.000%

    No Known Activations