© 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. 18469
    Prev
    Next
    INDEX
    Explanations

    when followed by it or you

    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
     therapeutic
    0.42
    溅
    0.40
     RNN
    0.38
     AppCompat
    0.37
     trafi
    0.37
     metaphors
    0.36
    頡
    0.36
     purpos
    0.36
    \%,
    0.36
     ओन
    0.35
    POSITIVE LOGITS
    there
    0.50
     ہوں۔
    0.43
    你是
    0.42
    étais
    0.42
     there
    0.41
    ულია
    0.39
    crack
    0.38
    ელია
    0.38
    Vous
    0.37
    感じる
    0.37
    Activations Density 0.071%

    No Known Activations