© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 195812
    Prev
    Next
    INDEX
    Explanations

    ricanes

    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
    ח
    0.17
    ית
    0.16
    ת
    0.16
     swoich
    0.16
    א
    0.15
    ות
    0.15
     richied
    0.15
    inizi
    0.14
    THAT
    0.14
    ע
    0.14
    POSITIVE LOGITS
    K
    0.25
    m
    0.25
    ll
    0.22
    b
    0.22
    J
    0.21
    d
    0.20
     are
    0.20
    G
    0.20
    것
    0.19
    D
    0.18
    Activations Density 0.002%

    No Known Activations