© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253005
    Prev
    Next
    INDEX
    Explanations

    sights

    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_56_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
     ($
    0.42
     live
    0.41
     {!
    0.39
    ก็ตาม
    0.38
    📻
    0.38
     going
    0.38
     मिलने
    0.37
     등으로
    0.37
    によって
    0.37
     அல்லது
    0.37
    POSITIVE LOGITS
    涉
    0.41
    ولد
    0.41
    трите
    0.38
     :}
    0.36
     inter
    0.35
     ያስፈል
    0.35
    affiliated
    0.35
     busc
    0.34
    গ্রে
    0.34
    onomic
    0.34
    Activations Density 0.008%

    No Known Activations