© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59274
    Prev
    Next
    INDEX
    Explanations

    tide or time

    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
    h
    1.98
    z
    1.43
    N
    1.20
    k
    1.18
    1.17
    .
    1.16
     време
    1.13
    이었
    1.13
    '
    1.13
    Time
    1.11
    POSITIVE LOGITS
    ی
    1.48
    ни
    1.37
    ру
    1.24
    ک
    1.15
    ives
    1.12
    ू
    1.12
    ну
    1.10
    ING
    1.09
    ﺪ
    1.08
    inati
    1.04
    Activations Density 0.000%

    No Known Activations