© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208640
    Prev
    Next
    INDEX
    Explanations

    customer interviews

    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_20_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
     labourers
    0.18
    AGER
    0.18
    नामेंट
    0.18
    藹
    0.17
    琰
    0.17
    wikidata
    0.17
     आवास
    0.16
    UTION
    0.16
     हॉकी
    0.16
     প্রণাম
    0.16
    POSITIVE LOGITS
     saa
    0.19
    self
    0.18
    hr
    0.18
     ،
    0.18
     ,
    0.18
     Ци
    0.18
     ص
    0.17
    เมริกา
    0.17
    ss
    0.17
     والت
    0.17
    Activations Density 0.001%

    No Known Activations