© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136645
    Prev
    Next
    INDEX
    Explanations

    default runtime context

    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_12_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
    ’
    0.43
    
    0.39
    …’
    0.37
    晨
    0.37
    <0xBA>
    0.33
    ’).
    0.33
    ’,
    0.31
    ্ড
    0.30
    ರ್‌
    0.30
    fourth
    0.30
    POSITIVE LOGITS
    а
    0.40
     на
    0.39
     за
    0.39
    ă
    0.39
     on
    0.39
     и
    0.38
     -
    0.38
    Пре
    0.38
    ،
    0.38
    П
    0.37
    Activations Density 0.000%

    No Known Activations