© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150163
    Prev
    Next
    INDEX
    Explanations

    mention of specific terms like "devil" or "SARS-CoV-2"

    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_18_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
     imperatives
    0.59
    vp
    0.55
    u
    0.53
     shootings
    0.53
     vouchers
    0.49
    z
    0.49
    c
    0.48
    na
    0.48
    वीपी
    0.48
     vp
    0.47
    POSITIVE LOGITS
    䡆
    0.47
     Pública
    0.45
    COMMENT
    0.44
     प्रॉपर्टी
    0.43
    Chọn
    0.43
     Celebration
    0.41
    <0x80>
    0.41
     Fum
    0.41
    𓏧
    0.41
     Çalış
    0.41
    Activations Density 0.000%

    No Known Activations