© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18756
    Prev
    Next
    INDEX
    Explanations

    hand gesture calling pointing

    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_34_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
     خلاف
    0.42
     LG
    0.42
    棘
    0.37
    遵
    0.37
     proced
    0.36
     proceed
    0.36
    LG
    0.35
    傲
    0.35
     Po
    0.35
    wal
    0.35
    POSITIVE LOGITS
    Pointing
    0.45
     pointing
    0.42
    pointing
    0.42
    呼び
    0.40
    Calling
    0.39
     chorus
    0.38
    calling
    0.38
     chamada
    0.36
     weaving
    0.36
     signalling
    0.36
    Activations Density 0.008%

    No Known Activations