© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130060
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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_25_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
    ulton
    0.19
     Medications
    0.19
     Measures
    0.18
    ﹒
    0.18
     Linguistics
    0.18
     Zert
    0.17
    frica
    0.17
    เภ
    0.17
    aratus
    0.17
     prescribing
    0.17
    POSITIVE LOGITS
    éssel
    0.18
    ősz
    0.17
     câte
    0.17
     suure
    0.17
    __["
    0.16
    Hug
    0.16
     centered
    0.16
     ho
    0.15
     erase
    0.15
     tramite
    0.15
    Activations Density 0.001%

    No Known Activations