© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3281
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_39_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
    childComplexity
    0.39
     ∣
    0.39
    igste
    0.39
    经历
    0.38
    堑
    0.38
    inue
    0.37
    седнев
    0.37
    BrNO
    0.36
    經歷
    0.36
     steep
    0.35
    POSITIVE LOGITS
    꾸
    0.43
    ža
    0.43
     musica
    0.40
    beach
    0.38
     Gazz
    0.38
     역
    0.37
     গড়ে
    0.36
     लार
    0.36
    ՞
    0.36
     Beach
    0.35
    Activations Density 0.000%

    No Known Activations