© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117038
    Prev
    Next
    INDEX
    Explanations

    consider context and limitations

    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_27_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
    🔥
    0.34
     campanha
    0.33
     muốn
    0.31
     Secondary
    0.30
     attempting
    0.30
     concurrent
    0.30
     campaña
    0.30
     candidate
    0.29
     Concurrent
    0.29
     машиналарын
    0.29
    POSITIVE LOGITS
    Punj
    0.32
    Ethn
    0.32
     осві
    0.31
    ρι
    0.30
     professionnels
    0.30
    臺
    0.30
    Բ
    0.29
    Bruno
    0.29
    ფ
    0.29
     subdue
    0.29
    Activations Density 0.007%

    No Known Activations