© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138655
    Prev
    Next
    INDEX
    Explanations

    Kannst du German conjugation

    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_12_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
    )],
    0.56
     orale
    0.50
     îl
    0.48
    хода
    0.48
    भिन्न
    0.47
    ?
    0.47
    Thời
    0.47
     अड्
    0.47
    вари
    0.46
    Пред
    0.46
    POSITIVE LOGITS
    телем
    0.49
    atuur
    0.46
    asjoner
    0.46
    iefert
    0.46
    Embed
    0.46
    ahnya
    0.45
    idden
    0.44
     hardened
    0.44
    琛
    0.44
    embed
    0.43
    Activations Density 0.008%

    No Known Activations