© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35396
    Prev
    Next
    INDEX
    Explanations

    PreviewProvider

    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
    >(
    0.46
    saya
    0.45
    நான்
    0.45
    新しい
    0.44
    ров
    0.44
     messed
    0.44
    because
    0.43
    consciously
    0.42
    мые
    0.41
    class
    0.40
    POSITIVE LOGITS
     r
    0.63
     calipers
    0.62
     obtiene
    0.54
     Config
    0.53
     caliper
    0.53
     kinetics
    0.51
     representa
    0.51
     verifica
    0.51
     momento
    0.49
     ff
    0.49
    Activations Density 0.000%

    No Known Activations