© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149457
    Prev
    Next
    INDEX
    Explanations

    numbers or quantities

    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_59_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
    hota
    0.39
    lera
    0.39
     Unterricht
    0.38
     Datensch
    0.37
     Nora
    0.36
     Gora
    0.36
    ennium
    0.36
    貂
    0.36
    ஶ
    0.35
     ระยะ
    0.35
    POSITIVE LOGITS
     like
    0.55
    Two
    0.42
    Four
    0.42
     মতো
    0.41
     LIKE
    0.41
     abilities
    0.40
    Like
    0.40
     couplings
    0.40
    як
    0.38
    four
    0.37
    Activations Density 0.002%

    No Known Activations