© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202664
    Prev
    Next
    INDEX
    Explanations

    Err(_) handling

    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_37_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
     Targeted
    0.43
     targeted
    0.39
    ньо
    0.38
    …………………………………………
    0.38
    ]?
    0.37
    ……………………
    0.36
    Cab
    0.36
    騨
    0.36
     সূ
    0.35
     früher
    0.35
    POSITIVE LOGITS
    হইতে
    0.41
     leash
    0.40
     অন্যান্য
    0.39
    ेश्वर
    0.39
     Lease
    0.39
     वेक्टर
    0.39
     Joints
    0.39
     altering
    0.38
     recoup
    0.38
    开发的
    0.37
    Activations Density 0.000%

    No Known Activations