© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76310
    Prev
    Next
    INDEX
    Explanations

    like

    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_31_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
     Kindly
    0.42
     inspiración
    0.40
     Küchen
    0.40
     Kitchen
    0.39
     kindly
    0.38
     Magellan
    0.38
    퐁
    0.38
    胞
    0.38
     Milling
    0.36
     หมด
    0.35
    POSITIVE LOGITS
    しみ
    0.43
    ཛ
    0.43
    ృత
    0.37
    trunk
    0.36
    orsum
    0.34
    𝓐
    0.34
    aysa
    0.33
     stø
    0.33
    Edt
    0.33
    ctree
    0.33
    Activations Density 0.051%

    No Known Activations