© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    Vader helmet, rock galactic, tank controls

    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_13_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
     use
    0.43
     s
    0.39
     ur
    0.35
    ur
    0.33
     sister
    0.33
     services
    0.32
     plumbing
    0.32
     unic
    0.32
     u
    0.31
     opio
    0.31
    POSITIVE LOGITS
    ítulos
    0.34
    anski
    0.34
    摶
    0.33
    ispiel
    0.33
    igneur
    0.33
    elijk
    0.33
     Verkehr
    0.33
     vésicules
    0.32
     त्रास
    0.32
    桦
    0.32
    Activations Density 0.070%

    No Known Activations