© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199537
    Prev
    Next
    INDEX
    Explanations

    file dialog titles

    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_12_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
    Cl
    0.47
    ers
    0.45
    cl
    0.44
    rate
    0.44
    js
    0.43
    sType
    0.43
    Daten
    0.42
    0
    0.42
    serif
    0.42
    para
    0.42
    POSITIVE LOGITS
     πολλ
    0.46
     שה
    0.46
     molti
    0.43
     peruse
    0.41
    からの
    0.41
     بل
    0.41
     devising
    0.41
    рен
    0.40
     бли
    0.39
     inan
    0.39
    Activations Density 0.001%

    No Known Activations