© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164835
    Prev
    Next
    INDEX
    Explanations

    detailed steps or options

    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_31_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
     responsive
    0.41
    િંહ
    0.39
    .|
    0.37
     Responsive
    0.37
     clearly
    0.37
     lac
    0.36
     retard
    0.36
     hearing
    0.36
    മായ
    0.36
     delay
    0.35
    POSITIVE LOGITS
    餬
    0.38
    నాన్ని
    0.36
    Michel
    0.36
    नामा
    0.35
    IsMethod
    0.35
     بوا
    0.35
    ORIA
    0.35
    ropo
    0.34
     pushedAt
    0.34
    点で
    0.34
    Activations Density 0.005%

    No Known Activations