© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197877
    Prev
    Next
    INDEX
    Explanations

    install X using pip

    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_27_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
    ҹ
    0.36
     söyled
    0.36
     vote
    0.35
    意的
    0.35
     insegn
    0.35
    ၟ
    0.34
     reservas
    0.34
     condense
    0.34
    }];
    0.34
     dessins
    0.34
    POSITIVE LOGITS
     Think
    0.41
     Episc
    0.41
    躹
    0.39
     Until
    0.39
     Pent
    0.39
     Mill
    0.38
     Himalayan
    0.38
     Math
    0.38
    Think
    0.38
     Title
    0.37
    Activations Density 0.001%

    No Known Activations