© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158528
    Prev
    Next
    INDEX
    Explanations

    birthday, university, or people's names like Anna

    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_2_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
    ta
    1.38
    '
    1.37
    i
    1.33
    cion
    1.27
    -
    1.26
    gers
    1.20
    to
    1.20
    can
    1.19
    that
    1.19
    ts
    1.18
    POSITIVE LOGITS
    ل
    1.41
    on
    1.38
    л
    1.23
    رك
    1.19
    не
    1.13
     созда
    1.09
    رج
    1.09
    رة
    1.09
     ४
    1.05
    رل
    1.05
    Activations Density 0.000%

    No Known Activations