© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    pronouns associated with body parts

    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
     মেয়র
    0.43
    eight
    0.38
     Leandro
    0.38
    lastCursor
    0.37
    wad
    0.37
    mayor
    0.37
     अधिसू
    0.37
    (/^\
    0.37
    ahooks
    0.36
     Ond
    0.35
    POSITIVE LOGITS
    free
    0.48
     free
    0.44
    Free
    0.44
    FREE
    0.41
     instrument
    0.40
    免费
    0.38
     свобод
    0.38
     حنا
    0.37
     arm
    0.37
     Free
    0.36
    Activations Density 0.057%

    No Known Activations