© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86812
    Prev
    Next
    INDEX
    Explanations

    detailed 3d models and scenes

    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_18_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
     yatha
    0.21
    "/"
    0.20
    akaranam
    0.20
     *@
    0.19
     exámenes
    0.19
    aparikkh
    0.19
     használ
    0.19
     dissati
    0.18
     halfCanvas
    0.18
     honti
    0.18
    POSITIVE LOGITS
     smashing
    0.18
    M
    0.18
    qu
    0.16
    H
    0.16
    er
    0.15
    OL
    0.14
     seven
    0.14
    QU
    0.14
     attacking
    0.14
    Oui
    0.14
    Activations Density 0.008%

    No Known Activations