© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165930
    Prev
    Next
    INDEX
    Explanations

    strength or strengths

    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_34_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
     Besitz
    0.39
    üp
    0.38
     tutorials
    0.37
    دأ
    0.36
    店
    0.36
    tutorials
    0.36
    ತನ
    0.36
    mAh
    0.35
     খাবারের
    0.34
     sicherlich
    0.34
    POSITIVE LOGITS
    膨
    0.44
    ething
    0.38
     Bul
    0.38
     expansión
    0.38
    expanding
    0.38
    Experience
    0.37
     woo
    0.37
    iolet
    0.37
     reformer
    0.37
     выход
    0.37
    Activations Density 0.001%

    No Known Activations