© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202715
    Prev
    Next
    INDEX
    Explanations

    thermo- variants

    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_6_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
    이었
    1.02
    the
    0.91
    щего
    0.86
    的需求
    0.82
    ativo
    0.81
    ઓ
    0.81
    ต์
    0.80
    的变化
    0.80
    的可
    0.80
    이가
    0.79
    POSITIVE LOGITS
    4
    1.29
     is
    1.28
    c
    1.28
    си
    1.14
    3
    1.13
     not
    1.12
    ↵↵
    1.09
    र
    1.07
    ר
    1.06
    9
    1.03
    Activations Density 0.001%

    No Known Activations