© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132209
    Prev
    Next
    INDEX
    Explanations

    birdhouse, feeder, baths

    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_6_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
    as
    1.40
    at
    1.16
    is
    1.16
    un
    1.14
    ，
    1.05
    ing
    1.02
    ：
    0.92
    ad
    0.91
    in
    0.91
    中
    0.88
    POSITIVE LOGITS
     I
    1.17
    ки
    1.17
    ید
    1.17
    ва
    1.11
    h
    1.05
     uang
    1.04
    iy
    1.02
     aider
    1.01
    ną
    1.00
    رهای
    0.98
    Activations Density 0.002%

    No Known Activations