© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82679
    Prev
    Next
    INDEX
    Explanations

    long-term, long-distance, long-lasting

    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_0_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
    л
    1.56
    ל
    1.41
    يد
    1.37
    ک
    1.30
    し
    1.29
    લ
    1.27
    يل
    1.22
    <0x0D>
    1.18
    ことを
    1.18
    ল
    1.16
    POSITIVE LOGITS
    '
    1.77
    W
    1.57
    K
    1.57
    O
    1.55
    IN
    1.53
    AN
    1.53
    U
    1.53
    I
    1.52
    AT
    1.52
    P
    1.48
    Activations Density 0.014%

    No Known Activations