© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160192
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ed
    1.33
    .
    1.23
    atas
    1.20
    eng
    1.18
    -
    1.17
    ick
    1.13
    ada
    1.12
    ant
    1.09
    etric
    1.07
    ase
    1.06
    POSITIVE LOGITS
    ח
    1.70
    ו
    1.60
    リ
    1.56
    و
    1.44
    ר
    1.41
    ك
    1.35
    وين
    1.34
    ка
    1.30
    the
    1.30
    на
    1.27
    Activations Density 0.000%

    No Known Activations