© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58134
    Prev
    Next
    INDEX
    Explanations

    Cyrillic text containing 'л'

    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
    ння
    1.36
    ется
    1.24
    <0x80>
    1.22
    ย
    0.89
     于
    0.87
    ωμα
    0.87
    يك
    0.86
    獷
    0.85
    емых
    0.85
    ющих
    0.84
    POSITIVE LOGITS
    z
    1.84
    N
    1.51
    can
    1.43
    et
    1.41
    j
    1.41
    x
    1.40
    ।
    1.38
    B
    1.34
    ۲
    1.34
    스
    1.32
    Activations Density 0.000%

    No Known Activations