© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103807
    Prev
    Next
    INDEX
    Explanations

    technique

    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_1_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
    ’
    1.76
    ר
    1.45
    ן
    1.45
    ર
    1.21
    น
    1.09
    นิ
    1.04
    2
    1.04
    ｒ
    1.03
     visor
    1.02
     sient
    1.01
    POSITIVE LOGITS
    ll
    1.48
    އ
    1.26
    im
    1.21
    væ
    1.21
    k
    1.19
    ك
    1.15
    um
    1.12
    kem
    1.11
    ls
    1.10
    vég
    1.09
    Activations Density 0.002%

    No Known Activations