© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140131
    Prev
    Next
    INDEX
    Explanations

    Yuan Dynasty names

    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_12_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
     ।”
    0.59
    ।”
    0.58
    ।,
    0.58
    。,
    0.57
     amyloid
    0.53
    Ｅ
    0.52
    える
    0.52
    ाये
    0.52
    Έ
    0.51
    𝐾
    0.49
    POSITIVE LOGITS
    =
    0.53
     Monster
    0.51
     dovuto
    0.51
     Mandarin
    0.49
     Cow
    0.49
     Crush
    0.48
     storia
    0.48
     Scholarship
    0.48
     Snapshot
    0.47
     Decoding
    0.47
    Activations Density 0.001%

    No Known Activations