© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201144
    Prev
    Next
    INDEX
    Explanations

    SO₄ ions

    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_12_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
     MILLER
    0.26
     conceded
    0.26
     dogged
    0.24
     количе
    0.24
    '
    0.23
     табли
    0.22
     devrez
    0.22
     conceding
    0.22
    율
    0.22
     recuerda
    0.22
    POSITIVE LOGITS
    jakarta
    0.25
    Universität
    0.25
    Ht
    0.23
    OL
    0.23
    ttt
    0.23
    tiff
    0.22
    .<
    0.22
    ellae
    0.22
    ✿
    0.22
    cation
    0.22
    Activations Density 0.001%

    No Known Activations