© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110207
    Prev
    Next
    INDEX
    Explanations

    proof of concept (PoC)

    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_2_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
    ট
    1.49
    स
    1.23
    ר
    1.15
    う
    1.13
    স
    1.10
    ש
    1.10
    ாவில்
    1.07
    не
    1.05
    ল
    0.96
    м
    0.94
    POSITIVE LOGITS
    .
    1.42
    _
    1.37
     of
    1.33
    p
    1.22
     =
    1.20
    ä
    1.20
    OD
    1.20
    al
    1.13
    RE
    1.13
    ty
    1.11
    Activations Density 0.001%

    No Known Activations