© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14512
    Prev
    Next
    INDEX
    Explanations

    dog breeds

    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_13_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
    /
    0.12
     dog
    0.12
     BUT
    0.11
    estic
    0.11
     puppies
    0.11
    Dog
    0.11
     but
    0.11
     canine
    0.11
     /
    0.11
     Π
    0.11
    POSITIVE LOGITS
     winkel
    0.11
     creencias
    0.11
     sobrevivir
    0.11
     acreditar
    0.10
    sley
    0.10
    த்துள்
    0.10
     unpre
    0.10
     সময়ে
    0.10
    സ്സ
    0.10
    satunya
    0.10
    Activations Density 0.058%

    No Known Activations