© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32096
    Prev
    Next
    INDEX
    Explanations

    where can i

    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_31_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
    걸
    0.37
     spacings
    0.35
    ASSIGN
    0.34
     complain
    0.33
    Rut
    0.33
     contribute
    0.33
     comply
    0.33
     understand
    0.32
    㕕
    0.32
     vanish
    0.31
    POSITIVE LOGITS
     matahari
    0.37
     vendita
    0.36
    uenza
    0.36
     neuer
    0.36
     mega
    0.35
     ஆழ்
    0.35
     الشه
    0.35
    colorControl
    0.35
     tapas
    0.34
     tussen
    0.34
    Activations Density 0.006%

    No Known Activations