© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110073
    Prev
    Next
    INDEX
    Explanations

    gehen, gehen wir

    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
     a
    1.52
    ка
    1.46
    ת
    1.29
    ing
    1.16
    ?
    1.13
     do
    1.13
     i
    1.09
    ة
    1.09
    ς
    1.04
    ви
    1.03
    POSITIVE LOGITS
    م
    1.69
    м
    1.25
    }">
    1.17
     Hrvatske
    1.12
    on
    1.11
    ル
    1.05
    杫
    1.05
    取り
    1.01
    去
    1.01
     hiszen
    0.99
    Activations Density 0.001%

    No Known Activations