© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135244
    Prev
    Next
    INDEX
    Explanations

    dwarf planets and asteroid belt

    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_37_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
    oggetto
    0.44
     Conseil
    0.44
    objeto
    0.41
    𝔻
    0.40
    ObjectIndex
    0.39
    オブジェクト
    0.39
    씽
    0.39
    𝚃
    0.39
     recomiendo
    0.38
    ServiceObject
    0.38
    POSITIVE LOGITS
    onedDateTime
    0.38
     Parks
    0.37
     dal
    0.37
     परिसर
    0.37
     sash
    0.37
     Ghe
    0.37
     Liv
    0.37
    ochi
    0.36
     globe
    0.36
     Masks
    0.36
    Activations Density 0.001%

    No Known Activations