© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4121
    Prev
    Next
    INDEX
    Explanations

    specific tasks

    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
    Jeg
    0.40
     consisted
    0.39
     ਟ
    0.38
    BLIC
    0.38
     verfügt
    0.38
    இரு
    0.37
    ausea
    0.37
    mentare
    0.36
     consists
    0.35
     embarking
    0.35
    POSITIVE LOGITS
     straws
    0.35
     राउ
    0.35
    नाती
    0.35
    த்துள்ளது
    0.34
     "**
    0.34
    全国
    0.34
     shoal
    0.34
    芽
    0.34
    ujemy
    0.34
     Grimes
    0.34
    Activations Density 0.164%

    No Known Activations