© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66358
    Prev
    Next
    INDEX
    Explanations

    guild ID, attribute, existential forgery

    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_41_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
     eased
    0.38
     செய்யப்படும்
    0.36
    ﹎
    0.35
    员
    0.35
    াম
    0.34
    問題
    0.34
    休息
    0.34
     wszel
    0.34
    低
    0.34
    ucksack
    0.33
    POSITIVE LOGITS
     ID
    0.47
    attribute
    0.46
     attr
    0.46
     attribute
    0.46
     Attribute
    0.46
    attr
    0.45
     attributes
    0.45
     IDs
    0.45
     atributos
    0.44
    attrs
    0.42
    Activations Density 0.010%

    No Known Activations