© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43280
    Prev
    Next
    INDEX
    Explanations

    offer information

    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_22_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
    집
    0.26
    莼
    0.25
     cuantit
    0.25
     subcut
    0.25
    website
    0.25
     quantitatively
    0.25
     organisatie
    0.25
     szervez
    0.25
    Abroad
    0.24
    铌
    0.24
    POSITIVE LOGITS
    ৃতির
    0.31
    疑问
    0.26
    タオル
    0.24
    Ws
    0.23
    xture
    0.23
     Mandel
    0.23
    Wr
    0.23
     Stevie
    0.23
    hmm
    0.22
     প্রশ্নের
    0.22
    Activations Density 0.067%

    No Known Activations