© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101075
    Prev
    Next
    INDEX
    Explanations

    think tanks and think tank publications

    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_14_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
    ங்கிணை
    0.57
    édération
    0.56
    ună
    0.55
    Deque
    0.55
    Group
    0.54
     ءِ
    0.54
    étiques
    0.54
    த்ரே
    0.54
     группы
    0.53
    äst
    0.53
    POSITIVE LOGITS
     preventing
    0.55
     ค
    0.54
     rite
    0.54
     та
    0.53
     circuit
    0.52
    k
    0.51
     world
    0.51
     prevent
    0.51
     it
    0.50
     la
    0.50
    Activations Density 0.000%

    No Known Activations