© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85449
    Prev
    Next
    INDEX
    Explanations

    computers thinking

    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_23_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
    叛
    0.41
     lesión
    0.40
    рал
    0.38
    φος
    0.37
     espè
    0.36
    💥
    0.35
     malesuada
    0.35
    }&\
    0.35
    bbene
    0.35
    过来
    0.35
    POSITIVE LOGITS
     inbuilt
    0.42
     Study
    0.40
     ፓ
    0.40
     STUDY
    0.40
     Chhattisgarh
    0.40
     study
    0.39
    study
    0.39
     \""
    0.39
     quilt
    0.38
     basil
    0.38
    Activations Density 0.010%

    No Known Activations