© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195190
    Prev
    Next
    INDEX
    Explanations

    best available information

    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_4_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
    fortunately
    0.76
    ्रिक
    0.74
    ین
    0.71
     estándares
    0.71
    м
    0.71
    as
    0.71
     стану
    0.70
    ну
    0.68
     interiores
    0.68
     ovales
    0.68
    POSITIVE LOGITS
     at
    1.05
     of
    0.84
     for
    0.80
    ות
    0.80
    t
    0.80
     by
    0.77
    é
    0.76
     on
    0.76
    지
    0.73
     -
    0.71
    Activations Density 0.000%

    No Known Activations