© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45852
    Prev
    Next
    INDEX
    Explanations

    covering body parts or surfaces

    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_22_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
     Shimizu
    0.17
     Hanna
    0.16
    ---
    0.16
     яко
    0.16
    ポ
    0.16
     Drake
    0.16
    Basically
    0.16
    /////////
    0.16
     Mock
    0.16
    Drake
    0.16
    POSITIVE LOGITS
     criticise
    0.19
     líneas
    0.19
    ીએ
    0.19
     ourselves
    0.18
     psychos
    0.18
     функциони
    0.18
     tensão
    0.18
     പ്രവര്‍ത്തന
    0.18
    ّر
    0.18
    בור
    0.18
    Activations Density 0.010%

    No Known Activations