© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166453
    Prev
    Next
    INDEX
    Explanations

    intricate details

    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_31_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
    稅
    0.42
    ภาษ
    0.41
     розмі
    0.40
    ตร
    0.40
    Ivoire
    0.39
    Maar
    0.39
    VhZ
    0.38
    ochlorite
    0.38
    citations
    0.37
     Serr
    0.37
    POSITIVE LOGITS
    妄
    0.39
    faux
    0.37
     faux
    0.37
     ribs
    0.36
     falsch
    0.36
     Rebel
    0.36
    伸ば
    0.36
     rib
    0.36
    )^(
    0.36
     buildings
    0.35
    Activations Density 0.005%

    No Known Activations