© 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. 14218
    Prev
    Next
    INDEX
    Explanations

    who is speaking

    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
     upheld
    0.39
     শরণার্থীরা
    0.38
     Mermaid
    0.38
     $((
    0.38
     गट
    0.36
     뒷
    0.36
    忄
    0.35
     უკ
    0.35
     Expansion
    0.35
    ्यु
    0.34
    POSITIVE LOGITS
     speaking
    1.39
    speaking
    1.24
    Speaking
    1.20
     Speaking
    1.16
    说话
    1.13
     speaks
    1.11
     konuş
    1.09
     berbicara
    1.09
     talking
    1.05
     speak
    1.05
    Activations Density 0.086%

    No Known Activations