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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196269
    Prev
    Next
    INDEX
    Explanations

    huggingface.co/docs or inference

    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_26_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
     đây
    0.35
    <code>
    0.35
     encrypt
    0.35
     এদের
    0.35
     HTTPS
    0.34
     autoimmunity
    0.34
     Dawn
    0.34
     endow
    0.34
     Chadwick
    0.34
     become
    0.33
    POSITIVE LOGITS
    Inputs
    0.44
    ERN
    0.42
    龔
    0.40
    ้น
    0.39
    抬头
    0.39
    රි
    0.38
    huang
    0.38
     spn
    0.38
     hamster
    0.37
    ाई
    0.37
    Activations Density 0.001%

    No Known Activations