© 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. 75830
    Prev
    Next
    INDEX
    Explanations

    yuan / currency amounts

    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
    ంచరీలు
    0.40
    ニュ
    0.39
    鐳
    0.39
    utor
    0.37
    ミネ
    0.37
    ʸ
    0.37
    akura
    0.36
    各位同學
    0.35
    镭
    0.35
     অপু
    0.35
    POSITIVE LOGITS
     leaf
    0.37
    莆
    0.36
    punct
    0.35
    ánea
    0.35
    雎
    0.35
    bia
    0.33
     Czy
    0.33
    '<
    0.32
     suena
    0.32
     Keb
    0.32
    Activations Density 0.004%

    No Known Activations