© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6420
    Prev
    Next
    INDEX
    Explanations

    welcome to

    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_39_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
     घरे
    0.40
     интернете
    0.40
     স্ত্র
    0.37
     conducting
    0.36
     विषयों
    0.36
     reasoning
    0.35
    hre
    0.35
    හ
    0.35
     रूपए
    0.35
     FIGURE
    0.34
    POSITIVE LOGITS
     Daniels
    0.40
    DateFormat
    0.38
    Sail
    0.38
    ন্তু
    0.38
     Advent
    0.38
     adventurer
    0.38
     आपले
    0.37
    राइट
    0.37
     Gunnar
    0.37
     Arms
    0.36
    Activations Density 0.004%

    No Known Activations