© 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. 158499
    Prev
    Next
    INDEX
    Explanations

    Spanish 'es'

    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
     is
    1.40
    ll
    1.39
    d
    1.38
    t
    1.27
    les
    1.13
    ls
    1.13
    lerin
    1.13
    1.13
    lijke
    1.09
    -
    1.09
    POSITIVE LOGITS
    و
    1.55
    O
    1.53
    at
    1.49
    ো
    1.42
    C
    1.34
    ع
    1.32
    G
    1.23
    T
    1.22
    B
    1.22
    ین
    1.21
    Activations Density 0.004%

    No Known Activations