© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53400
    Prev
    Next
    INDEX
    Explanations

    is for sale

    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_30_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
     "?"]
    0.47
    逪
    0.42
     deviennent
    0.40
    BALANCE
    0.39
    ᴹ
    0.39
     понять
    0.39
     italien
    0.39
    दरअसल
    0.37
     तिथ
    0.37
    噵
    0.37
    POSITIVE LOGITS
     suitable
    0.38
    ජ
    0.37
    prototype
    0.37
     impregnated
    0.37
    엎
    0.36
    オリ
    0.36
     spatially
    0.36
     prototypes
    0.36
     developmentally
    0.35
     knuckles
    0.35
    Activations Density 0.000%

    No Known Activations