© 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. 126221
    Prev
    Next
    INDEX
    Explanations

    ARO AARP AB ABC

    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
    ك
    0.86
    a
    0.84
    ل
    0.76
    비
    0.76
    ه
    0.72
    с
    0.69
    కు
    0.69
     Macri
    0.66
    ル
    0.66
    ተት
    0.64
    POSITIVE LOGITS
    ances
    0.65
    রা
    0.65
    ER
    0.60
    ния
    0.60
    zione
    0.60
     u
    0.59
     questionnaires
    0.59
    aksi
    0.59
     prominent
    0.58
     wavelengths
    0.58
    Activations Density 0.023%

    No Known Activations