© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 66414
    Prev
    Next
    INDEX
    Explanations

    game resources

    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
    Monkey
    0.38
    copper
    0.36
    ную
    0.36
    ोरा
    0.35
    胸
    0.35
     Freed
    0.35
     Pomer
    0.35
     lizard
    0.34
     terr
    0.34
    흉
    0.34
    POSITIVE LOGITS
     resources
    0.50
     ресур
    0.48
     residues
    0.47
    Resources
    0.45
    resources
    0.45
     recursos
    0.44
     residuals
    0.42
    资源
    0.42
    residuals
    0.41
    资源的
    0.40
    Activations Density 0.006%

    No Known Activations