© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202167
    Prev
    Next
    INDEX
    Explanations

    listen and repeat

    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_46_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
     مطلق
    0.46
    presas
    0.43
    خراج
    0.42
    }^{+\
    0.42
     بہت
    0.40
    odoxy
    0.39
    passwd
    0.39
     ნახ
    0.38
    naires
    0.38
    䘚
    0.38
    POSITIVE LOGITS
     Neu
    0.41
     Monter
    0.39
     catalytic
    0.38
     neu
    0.38
     Shang
    0.36
     PSA
    0.36
     Pine
    0.36
     Auss
    0.35
     동시에
    0.35
     ETL
    0.35
    Activations Density 0.000%

    No Known Activations