© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107022
    Prev
    Next
    INDEX
    Explanations

    thoth, thiamin

    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_1_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
    8
    1.22
    6
    1.20
    ۹
    1.19
    ং
    1.16
    ić
    1.12
    es
    1.11
    em
    1.10
    9
    1.10
    し
    1.10
    は
    1.09
    POSITIVE LOGITS
    า
    1.10
     trove
    1.01
    ή
    0.93
    я
    0.88
    ור
    0.85
    ')
    0.84
    )
    0.84
    ก
    0.83
    ک
    0.83
    st
    0.82
    Activations Density 0.001%

    No Known Activations