© 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. 109794
    Prev
    Next
    INDEX
    Explanations

    sehr + adjective/noun

    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
    quela
    1.51
    quele
    1.45
    л
    1.44
    an
    1.34
    se
    1.30
    ك
    1.25
    נ
    1.18
    ان
    1.08
    வ
    1.08
    ول
    1.07
    POSITIVE LOGITS
     by
    1.28
    el
    1.06
    +
    1.05
     chmod
    1.03
    em
    1.00
    쐞
    0.99
     vaccin
    0.96
     Schreiben
    0.96
     contrat
    0.95
     którym
    0.95
    Activations Density 0.000%

    No Known Activations