© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196878
    Prev
    Next
    INDEX
    Explanations

    identify trends

    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
    unti
    0.44
     वैलेंट
    0.43
    UNT
    0.38
    tuned
    0.37
    罗
    0.37
     במס
    0.37
     ಲೋ
    0.36
     Determining
    0.36
    şi
    0.36
     רו
    0.36
    POSITIVE LOGITS
     regimes
    0.43
    ക്കാര്‍
    0.42
    ='".$
    0.40
    \%$
    0.38
     নিকটে
    0.38
     तेंद
    0.38
    \}.
    0.37
     dynast
    0.37
     regime
    0.37
     достой
    0.37
    Activations Density 0.003%

    No Known Activations