© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176379
    Prev
    Next
    INDEX
    Explanations

    computer hardware

    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_50_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
     Jaan
    0.48
     Latvia
    0.44
    ўкі
    0.43
     JAN
    0.42
    𒊑
    0.41
     Call
    0.40
    παϊ
    0.40
    YAN
    0.39
     jan
    0.39
     Jai
    0.39
    POSITIVE LOGITS
    marginStart
    0.46
    Х
    0.45
    H
    0.44
    fx
    0.41
    igma
    0.40
    Henry
    0.38
    SAM
    0.38
    itioners
    0.38
    しよう
    0.38
    XH
    0.38
    Activations Density 0.023%

    No Known Activations