© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60114
    Prev
    Next
    INDEX
    Explanations

    messages hear about

    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_11_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
    R
    0.41
    ’
    0.38
     vous
    0.37
    ME
    0.36
    is
    0.35
    as
    0.35
    ig
    0.35
    '
    0.35
    F
    0.35
     Information
    0.35
    POSITIVE LOGITS
     horribly
    0.36
     завод
    0.35
     afterlife
    0.34
     terribly
    0.33
    ింది
    0.33
    кона
    0.32
     raindrops
    0.32
     criminality
    0.32
     simonsen
    0.32
    addProduct
    0.32
    Activations Density 0.000%

    No Known Activations