© 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. 82122
    Prev
    Next
    INDEX
    Explanations

    filing cabinet and government cabinet

    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
     and
    1.41
     is
    1.26
    ला
    1.23
    می
    1.20
     जानना
    1.17
    '
    1.16
     to
    1.15
    い
    1.14
    чи
    1.13
    ро
    1.12
    POSITIVE LOGITS
    3
    1.73
    4
    1.66
    u
    1.53
    5
    1.52
    6
    1.49
    7
    1.44
    يد
    1.40
    X
    1.37
     étroite
    1.25
    Б
    1.25
    Activations Density 0.000%

    No Known Activations