© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65849
    Prev
    Next
    INDEX
    Explanations

    conjunctions/particles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    гово
    0.36
     Canyon
    0.34
     cab
    0.34
     ===========
    0.34
     cabs
    0.34
     Dafür
    0.34
    yship
    0.34
     h
    0.34
    の上
    0.33
     hey
    0.33
    POSITIVE LOGITS
     саме
    0.44
    ራም
    0.41
     sich
    0.41
    Strict
    0.41
    蘋
    0.40
    Survived
    0.40
     justement
    0.39
     zich
    0.38
     appunto
    0.38
     江
    0.38
    Activations Density 0.003%

    No Known Activations