© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53748
    Prev
    Next
    INDEX
    Explanations

    designating concepts

    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_55_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
     Edmonds
    0.41
    ことができます
    0.37
    arlan
    0.36
     خور
    0.35
    sqcup
    0.35
    彎
    0.34
    erdas
    0.34
    哩
    0.34
    டிய
    0.33
     Harlan
    0.33
    POSITIVE LOGITS
     designations
    0.39
     footprint
    0.39
     markers
    0.38
     índice
    0.37
     municipality
    0.37
    achen
    0.36
     genome
    0.36
    爽
    0.36
     antib
    0.36
    Spiel
    0.35
    Activations Density 0.055%

    No Known Activations