© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130809
    Prev
    Next
    INDEX
    Explanations

    squish, diminished, together

    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_1_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
    0
    1.80
    an
    1.77
    a
    1.68
    ;
    1.54
    to
    1.47
    ه
    1.47
    1
    1.45
    R
    1.45
    N
    1.40
    S
    1.39
    POSITIVE LOGITS
     dificultades
    1.27
     visione
    1.26
    iyorum
    1.23
    kannya
    1.21
    یان
    1.18
     conciencia
    1.17
     ﺍﻟ
    1.17
    ﻌ
    1.16
    ﻊ
    1.16
    üğü
    1.15
    Activations Density 0.000%

    No Known Activations