© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200867
    Prev
    Next
    INDEX
    Explanations

    places before 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_37_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
     ahorita
    0.41
     Mankind
    0.40
    伎
    0.38
     কোষ
    0.38
     ZO
    0.38
    舷
    0.37
     méxico
    0.37
     পদার্থের
    0.36
     XXIII
    0.36
    σμ
    0.36
    POSITIVE LOGITS
     minimize
    0.39
     task
    0.39
     field
    0.39
    ileri
    0.38
     complex
    0.37
     once
    0.36
     impact
    0.36
     minim
    0.36
     plains
    0.36
    /-
    0.36
    Activations Density 0.000%

    No Known Activations