© 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. 52938
    Prev
    Next
    INDEX
    Explanations

    metal followed by specific words

    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
     Matter
    0.37
     Conse
    0.37
     ማ
    0.36
    闹
    0.36
     Iron
    0.36
    вобо
    0.36
     Moore
    0.36
     Updating
    0.36
    鉐
    0.36
     நக
    0.36
    POSITIVE LOGITS
     солнца
    0.42
    Sunglasses
    0.42
    INTE
    0.40
    Compact
    0.39
    noxious
    0.37
    ळख
    0.37
    通道
    0.36
    乖
    0.36
    council
    0.35
     underground
    0.35
    Activations Density 0.001%

    No Known Activations