© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11461
    Prev
    Next
    INDEX
    Explanations

    map entry iteration

    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_40_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
    Hash
    0.48
     hashes
    0.41
     Hash
    0.40
     Hagen
    0.40
    hashes
    0.39
    Hashing
    0.38
    䏹
    0.36
    IfNot
    0.36
     hash
    0.36
    䀖
    0.36
    POSITIVE LOGITS
     testicule
    0.37
    RNB
    0.37
     string
    0.36
    ত্ব
    0.36
    ingresso
    0.35
     slices
    0.35
     matrícula
    0.35
    string
    0.34
     Mons
    0.34
    を集
    0.34
    Activations Density 0.041%

    No Known Activations