© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201337
    Prev
    Next
    INDEX
    Explanations

    ™ Technology, ® Proof, Pass, Plus, Complex, Assistant, Safe

    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
    ®
    1.62
     ®
    1.47
    ®,
    1.38
    ®.
    1.38
     ™
    1.18
    ™
    1.18
     trademark
    1.17
    Ⓡ
    1.10
    ©
    1.09
    ™,
    1.05
    POSITIVE LOGITS
    herr
    0.38
    elier
    0.36
     മനസ്സ
    0.35
    揆
    0.35
    enson
    0.34
    дина
    0.34
    Brazil
    0.34
    ნა
    0.34
    PrefabAsset
    0.34
     ʼ
    0.34
    Activations Density 0.010%

    No Known Activations