© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20232
    Prev
    Next
    INDEX
    Explanations

    Turkish

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     de
    0.87
     də
    0.62
    de
    0.57
     де
    0.55
     дә
    0.45
    De
    0.42
    <0xA4>
    0.42
     De
    0.42
    Esse
    0.41
     grounded
    0.40
    POSITIVE LOGITS
     da
    3.09
     да
    2.52
    da
    2.08
    Da
    2.00
     Da
    1.98
     دا
    1.89
     DA
    1.55
    دا
    1.43
     दा
    1.37
     다
    1.34
    Activations Density 0.001%

    No Known Activations