© 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. 143934
    Prev
    Next
    INDEX
    Explanations

    signed URLs, assigned tasks, resigned feelings

    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
    be
    1.30
    ia
    1.23
    DeviceId
    1.22
     На
    1.20
     Ж
    1.19
    ura
    1.18
     FISA
    1.16
    ku
    1.15
    javascripts
    1.12
    ki
    1.11
    POSITIVE LOGITS
    '
    1.75
    ти
    1.58
    ה
    1.48
    ین
    1.45
    ه
    1.43
    ു
    1.36
    ม
    1.36
    r
    1.34
    ס
    1.33
     realizar
    1.32
    Activations Density 0.000%

    No Known Activations