© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158496
    Prev
    Next
    INDEX
    Explanations

    RoPE scaling or extension

    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
     poodle
    0.97
     активность
    0.94
     genitals
    0.93
    ной
    0.92
    ão
    0.90
    د
    0.90
     точка
    0.86
    ς
    0.86
    िर
    0.86
     indigo
    0.86
    POSITIVE LOGITS
    et
    1.54
    de
    1.26
    ed
    1.20
    el
    1.17
    am
    1.16
    i
    1.15
    ות
    1.06
    ០
    1.02
    富有
    0.98
    zelfde
    0.98
    Activations Density 0.000%

    No Known Activations