© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 57676
    Prev
    Next
    INDEX
    Explanations

    narrative descriptions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    '।
    0.51
     seem
    0.51
    ।'
    0.51
    !'
    0.50
     !"
    0.50
    ).'
    0.49
     ="
    0.47
    '=
    0.46
     ='
    0.45
     bring
    0.44
    POSITIVE LOGITS
     allowed
    0.49
    met
    0.44
     permitió
    0.40
    bies
    0.40
    .
    0.40
     lets
    0.39
    ায়
    0.38
    sharp
    0.38
    packages
    0.37
    允许
    0.37
    Activations Density 0.011%

    No Known Activations