© 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. 41189
    Prev
    Next
    INDEX
    Explanations

    Scott Alexander, Tech, tape, masters

    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
    ت
    0.79
    ية
    0.77
    ై
    0.73
     Faculdade
    0.71
     Linie
    0.70
     Enroll
    0.69
    ش
    0.69
    ة
    0.69
     مركز
    0.69
    يت
    0.68
    POSITIVE LOGITS
    ﻢ
    0.74
    rası
    0.65
     micrograms
    0.62
    erland
    0.61
    field
    0.61
    γον
    0.61
     i
    0.61
    vention
    0.59
    ﻞ
    0.59
     o
    0.59
    Activations Density 0.004%

    No Known Activations