© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211988
    Prev
    Next
    INDEX
    Explanations

    under the hood

    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_5_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
    )$:
    1.02
     bestätigt
    0.97
    üşt
    0.96
     ভাইয়ের
    0.94
     manière
    0.93
     cinquième
    0.92
     caméra
    0.92
     şekilde
    0.92
     développé
    0.91
     disulfide
    0.91
    POSITIVE LOGITS
    ุ
    1.79
    s
    1.76
    ر
    1.56
    ی
    1.48
    l
    1.41
    ר
    1.38
     R
    1.35
     A
    1.34
    u
    1.34
    र
    1.34
    Activations Density 0.000%

    No Known Activations