© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30895
    Prev
    Next
    INDEX
    Explanations

    Kuiper Belt or similar sounds

    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_40_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
     Rot
    0.37
    veys
    0.36
     Blot
    0.36
    Rot
    0.34
     ملے
    0.34
    }},\
    0.34
    ROT
    0.34
     scratching
    0.33
    indazol
    0.33
    Od
    0.33
    POSITIVE LOGITS
    콰
    0.41
     Kuy
    0.41
    byshev
    0.38
     kua
    0.37
     صنعت
    0.37
    Kui
    0.36
     কৃত
    0.36
     kuy
    0.36
    wrong
    0.35
     Kui
    0.35
    Activations Density 0.013%

    No Known Activations