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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213111
    Prev
    Next
    INDEX
    Explanations

    HCI conferences

    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
    :
    1.28
    il
    1.11
    ik
    1.04
     cortos
    1.02
     autopilot
    1.00
    ้
    0.97
    '
    0.97
     excruciating
    0.95
     appendices
    0.95
    \
    0.95
    POSITIVE LOGITS
    r
    1.52
    m
    1.45
    of
    1.40
    o
    1.24
    p
    1.23
    ร
    1.23
    v
    1.16
    on
    1.13
    กับ
    1.13
    h
    1.13
    Activations Density 0.000%

    No Known Activations