© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195216
    Prev
    Next
    INDEX
    Explanations

    public information

    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_4_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
    '
    0.64
     Technik
    0.54
     tek
    0.52
     tinggal
    0.52
     Kamis
    0.52
     Cleaner
    0.52
     Calibri
    0.51
     Emission
    0.50
     Tempat
    0.50
    怿
    0.50
    POSITIVE LOGITS
    U
    0.54
    u
    0.53
    ine
    0.49
    iatric
    0.48
    id
    0.47
    G
    0.47
    onial
    0.45
    *}
    0.45
    name
    0.44
     léka
    0.44
    Activations Density 0.000%

    No Known Activations