© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230272
    Prev
    Next
    INDEX
    Explanations

    mein German phrases

    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_6_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
     Τ
    0.88
    는
    0.85
    5
    0.84
     บ
    0.83
     hypothes
    0.82
     outlay
    0.79
    âche
    0.78
    ck
    0.75
     Մ
    0.75
    ick
    0.72
    POSITIVE LOGITS
    er
    1.62
    on
    1.33
    ر
    1.31
    en
    1.30
    ার
    1.27
    ل
    1.27
    lardan
    1.24
    ре
    1.23
    ان
    1.21
    ів
    1.15
    Activations Density 0.000%

    No Known Activations