© 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. 107087
    Prev
    Next
    INDEX
    Explanations

    pyridine, derivative, Russian stems

    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
    0
    1.28
    1
    1.27
    3
    1.21
    2
    1.20
    that
    1.12
    r
    1.07
    line
    1.06
    5
    1.05
    ’
    1.05
    were
    1.00
    POSITIVE LOGITS
    в
    1.26
    ल
    1.20
    ,
    1.16
    น
    1.14
    ם
    1.13
     on
    1.09
     as
    1.09
    व
    1.08
    昰
    1.08
    ма
    1.07
    Activations Density 0.000%

    No Known Activations