© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90228
    Prev
    Next
    INDEX
    Explanations

    easy to use

    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_3_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
    I
    0.73
    abcdef
    0.56
     ponencia
    0.55
    A
    0.54
     I
    0.54
    neath
    0.54
    storey
    0.53
    pmatrix
    0.52
    sson
    0.52
     थी
    0.51
    POSITIVE LOGITS
    യുടെ
    0.75
    、
    0.73
    TIME
    0.72
     are
    0.69
    り
    0.68
    、「
    0.68
    RO
    0.65
     jogo
    0.65
     serviços
    0.65
    ），
    0.64
    Activations Density 0.001%

    No Known Activations