© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83142
    Prev
    Next
    INDEX
    Explanations

    sorting lists

    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_0_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
     for
    1.70
    ES
    1.59
    ER
    1.52
     on
    1.33
    G
    1.30
    }$.
    1.30
    7
    1.27
     It
    1.19
    EN
    1.19
    k
    1.16
    POSITIVE LOGITS
    ä
    1.73
    ိ
    1.30
    -
    1.30
    aient
    1.24
    ના
    1.23
    고
    1.23
    ке
    1.20
    ästä
    1.20
    し
    1.19
    い
    1.15
    Activations Density 0.001%

    No Known Activations