© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194310
    Prev
    Next
    INDEX
    Explanations

    thought experiment

    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_15_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
    Append
    0.19
    indd
    0.18
    äub
    0.18
    ില്ല
    0.18
    ներ
    0.18
    ிருந்த
    0.17
    inn
    0.17
    };\
    0.17
    ግዳ
    0.17
    itelisted
    0.17
    POSITIVE LOGITS
     jur
    0.20
     delito
    0.18
     cac
    0.18
    Y
    0.18
     bütün
    0.18
     lider
    0.18
     agencia
    0.18
     школы
    0.17
     प्रो
    0.17
    企业的
    0.17
    Activations Density 0.012%

    No Known Activations