© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174999
    Prev
    Next
    INDEX
    Explanations

    rotation speed

    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_20_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
    profiss
    0.45
     اهلا
    0.43
     kaks
    0.42
     рациона
    0.42
     disclosed
    0.41
    ');
    0.41
     kant
    0.40
     града
    0.38
     deleterious
    0.38
    }}$;
    0.38
    POSITIVE LOGITS
    POM
    0.49
    पूर
    0.46
     inac
    0.45
    ச்சர்
    0.44
     matchups
    0.43
    PUR
    0.42
    pom
    0.41
    দ্ভুত
    0.41
    JVM
    0.41
    ប្រភេទ
    0.40
    Activations Density 0.001%

    No Known Activations