© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38367
    Prev
    Next
    INDEX
    Explanations

    specification separator

    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_57_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
     runs
    0.40
    atz
    0.38
    These
    0.36
     వీటి
    0.36
    itte
    0.35
    ectors
    0.35
     어렵
    0.35
    這
    0.34
    {{
    0.34
     worried
    0.34
    POSITIVE LOGITS
     lla
    0.49
    ssä
    0.48
    lla
    0.48
    ssa
    0.46
    lls
    0.45
    stä
    0.44
    llä
    0.43
    sta
    0.42
     lle
    0.42
    ta
    0.39
    Activations Density 0.004%

    No Known Activations