© 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. 60178
    Prev
    Next
    INDEX
    Explanations

    coding instructions

    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
     a
    1.52
     be
    1.37
    (
    1.33
    ।
    1.27
    。
    1.20
     the
    1.20
    }
    1.18
    ка
    1.16
     y
    1.13
    ا
    1.13
    POSITIVE LOGITS
    f
    1.52
    ле
    1.24
    an
    1.23
    v
    1.23
    િ
    1.17
    i
    1.13
    b
    1.13
    l
    1.09
    栤
    1.09
    ری
    1.06
    Activations Density 0.002%

    No Known Activations