© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163702
    Prev
    Next
    INDEX
    Explanations

    Amsterdam Dutch promotion

    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_13_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
     verke
    0.50
     K
    0.47
     Queste
    0.47
     Chance
    0.46
     killing
    0.46
    𝐩
    0.46
     Kata
    0.45
     secund
    0.44
     Creature
    0.44
     Mercantile
    0.44
    POSITIVE LOGITS
    Cue
    0.46
     пригла
    0.46
    Bx
    0.45
    Lymph
    0.45
    IVITY
    0.44
    itati
    0.44
    À
    0.43
    Bris
    0.43
    lichting
    0.43
    IT
    0.43
    Activations Density 0.000%

    No Known Activations