© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233492
    Prev
    Next
    INDEX
    Explanations

    methane and hydrogen

    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_46_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
    REPO
    0.40
    ಾದರೂ
    0.39
    libs
    0.38
    чек
    0.38
    ète
    0.37
    ček
    0.37
    竖
    0.37
    хе
    0.37
     salespeople
    0.37
    HE
    0.36
    POSITIVE LOGITS
     Ei
    0.42
     ei
    0.38
     grasses
    0.37
     жи
    0.36
     CM
    0.36
    onuclear
    0.35
    cribable
    0.35
     attributed
    0.35
    白的
    0.35
    蒸汽
    0.35
    Activations Density 0.004%

    No Known Activations