© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261258
    Prev
    Next
    INDEX
    Explanations

    discrete signal and transform

    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_5_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
    is
    1.84
    یک
    1.13
    ações
    1.07
    uves
    1.07
    enangan
    1.07
    y
    1.07
    وی
    1.06
    isub
    1.05
    isst
    1.05
     pouches
    1.04
    POSITIVE LOGITS
     of
    1.25
     is
    1.18
     has
    1.13
     that
    1.05
    ط
    1.04
    tx
    1.03
     OF
    1.02
    sk
    1.00
    tl
    1.00
    ש
    0.99
    Activations Density 0.001%

    No Known Activations