© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150580
    Prev
    Next
    INDEX
    Explanations

    overlooked / take for granted

    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_23_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
     yayın
    0.48
    粎
    0.45
     düğ
    0.44
    ął
    0.42
     இயந்திர
    0.41
    顿
    0.41
    দ্য
    0.40
     duvar
    0.40
    粓
    0.39
    <unused324>
    0.39
    POSITIVE LOGITS
     possessions
    0.46
    Help
    0.39
    Media
    0.39
    quier
    0.39
     should
    0.38
     complements
    0.38
    NL
    0.38
    ጾ
    0.37
    Timed
    0.36
    笠
    0.36
    Activations Density 0.001%

    No Known Activations