© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54264
    Prev
    Next
    INDEX
    Explanations

    combined ideas and sentences

    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_31_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
     LSM
    0.41
     Mormon
    0.39
     중간
    0.38
     BMI
    0.38
     Cuts
    0.36
     demi
    0.35
    Ln
    0.35
    詞
    0.35
     withd
    0.35
    咸
    0.35
    POSITIVE LOGITS
    imilar
    0.40
     மான
    0.39
    νού
    0.38
     accomplishing
    0.37
     kori
    0.37
     accomplishment
    0.37
    entin
    0.37
     încă
    0.36
     identically
    0.36
    uelle
    0.36
    Activations Density 0.004%

    No Known Activations