© 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. 131149
    Prev
    Next
    INDEX
    Explanations

    general phrases

    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
    ব্যা
    0.42
     kayaking
    0.40
     ದೇ
    0.38
    ucius
    0.37
     καλ
    0.36
    di
    0.35
    couch
    0.35
    㐬
    0.35
     ব্যা
    0.35
    后端
    0.35
    POSITIVE LOGITS
    드리
    0.39
    ishing
    0.38
    hesive
    0.38
     frames
    0.37
    ished
    0.37
    REF
    0.37
    ografi
    0.37
     Ref
    0.36
     mio
    0.36
    mmHg
    0.36
    Activations Density 0.007%

    No Known Activations