© 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. 160077
    Prev
    Next
    INDEX
    Explanations

    siestafiestaSiete Leguas

    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
    ن
    1.63
    ס
    1.45
    ד
    1.35
    ק
    1.23
    س
    1.14
    اس
    1.10
    น
    1.02
    in
    1.02
    sin
    0.96
    ص
    0.96
    POSITIVE LOGITS
    -
    1.21
    에
    1.20
    ﻟ
    1.12
    পত্রের
    1.03
    >
    1.03
    ﺎ
    1.02
    to
    1.01
    に
    1.00
     régler
    0.95
    IS
    0.94
    Activations Density 0.000%

    No Known Activations