© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33117
    Prev
    Next
    INDEX
    Explanations

    social media or coding

    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_40_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
     KIND
    0.41
     pescado
    0.41
     விளக்கம்
    0.41
    攒
    0.39
     மீன
    0.37
     अष्टमी
    0.37
     समानार्थी
    0.36
     திரி
    0.36
    潇
    0.36
     LTP
    0.36
    POSITIVE LOGITS
     Staten
    0.40
    idget
    0.38
     CIA
    0.38
    arens
    0.38
    AZ
    0.37
     Bethel
    0.37
    шире
    0.37
     edges
    0.36
    CIA
    0.36
     Treas
    0.35
    Activations Density 0.014%

    No Known Activations