© 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. 126599
    Prev
    Next
    INDEX
    Explanations

    business plan or project plan

    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
    jats
    0.40
    Após
    0.38
    pekt
    0.37
    欣
    0.37
    annya
    0.35
     После
    0.35
    ídu
    0.35
    πτυ
    0.35
     clubhouse
    0.35
     Tada
    0.34
    POSITIVE LOGITS
     preced
    0.44
     थाना
    0.37
     disney
    0.37
    ipramine
    0.37
     gmail
    0.36
    ériques
    0.36
    シェル
    0.35
    睫
    0.34
     फ्लिप
    0.34
    شم
    0.33
    Activations Density 0.014%

    No Known Activations