© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89613
    Prev
    Next
    INDEX
    Explanations

    Swiss Mountain Dog

    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_11_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
    انس
    0.48
    ung
    0.41
    名
    0.40
     fanatic
    0.40
    θυν
    0.39
    backgroundSplit
    0.39
     principalColumn
    0.39
    心
    0.39
    juna
    0.39
    しゃ
    0.39
    POSITIVE LOGITS
     corrobor
    0.48
     These
    0.46
     Архиви
    0.46
     They
    0.45
     econometric
    0.44
     To
    0.44
     extrapolate
    0.44
     describir
    0.44
     these
    0.44
     catchment
    0.43
    Activations Density 0.033%

    No Known Activations