© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125569
    Prev
    Next
    INDEX
    Explanations

    SSH tunnel

    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
    wow
    0.90
    ick
    0.69
    best
    0.67
    b
    0.66
     Wow
    0.66
    cal
    0.65
    pf
    0.64
    ado
    0.63
    col
    0.63
    cken
    0.63
    POSITIVE LOGITS
    ﾙ
    0.73
    ו
    0.68
     descend
    0.66
     sytu
    0.64
     parametr
    0.64
     раствор
    0.64
     analy
    0.63
     observado
    0.63
     soupe
    0.63
     shifts
    0.62
    Activations Density 0.005%

    No Known Activations