© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 44378
    Prev
    Next
    INDEX
    Explanations

    even if you aren't experiencing

    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_22_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
    Cntr
    0.39
    '))->
    0.36
    的部分
    0.36
    )`;
    0.36
     우리의
    0.36
    }}=\
    0.35
    使用的是
    0.35
    ểm
    0.35
    ))=\
    0.35
    인다
    0.34
    POSITIVE LOGITS
    筝
    0.39
     orchestral
    0.37
    вина
    0.36
    joining
    0.35
    ه‌ای
    0.35
    bajo
    0.35
     affiliation
    0.35
    innings
    0.34
    ിലുള്ള
    0.34
     Exploration
    0.34
    Activations Density 0.008%

    No Known Activations