© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217282
    Prev
    Next
    INDEX
    Explanations

    Holden

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    jali
    0.39
    lán
    0.37
     Elli
    0.37
    স্বরূপ
    0.36
    ørte
    0.36
    ítom
    0.36
    SO
    0.35
    素
    0.35
    脊
    0.35
     সম্ম
    0.35
    POSITIVE LOGITS
     pile
    0.48
    pile
    0.44
    Pile
    0.44
     Pile
    0.43
     plag
    0.40
     cl
    0.40
    ിത്ര
    0.40
     succeed
    0.39
    PUS
    0.39
    onav
    0.38
    Activations Density 0.000%

    No Known Activations