© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157356
    Prev
    Next
    INDEX
    Explanations

    gef followed by German sentiment 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_2_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
    O
    1.70
     I
    1.36
    TI
    1.24
    Τ
    1.23
    ’
    1.23
    К
    1.23
     The
    1.20
     ouv
    1.20
    Μ
    1.18
    т
    1.17
    POSITIVE LOGITS
    {//
    1.20
    ون
    1.13
    {
    1.10
    った
    1.05
    az
    1.02
    ches
    0.98
    тата
    0.96
    av
    0.95
    ä
    0.94
    çado
    0.94
    Activations Density 0.000%

    No Known Activations