© 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. 203245
    Prev
    Next
    INDEX
    Explanations

    Name Carlos

    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
     рейтин
    0.45
     веществ
    0.41
     Jab
    0.40
    Dihydro
    0.38
     Planetary
    0.38
    ᱵ
    0.38
     Transplant
    0.37
    jab
    0.36
     moléculas
    0.36
     вещества
    0.36
    POSITIVE LOGITS
     পড়েন
    0.49
    formance
    0.40
     почита
    0.39
    本事
    0.38
     सर्विस
    0.37
     개
    0.37
     papers
    0.36
    itto
    0.36
     paper
    0.36
     falls
    0.36
    Activations Density 0.000%

    No Known Activations