© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35766
    Prev
    Next
    INDEX
    Explanations

    in the traditional sense

    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_31_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
     Quantification
    0.25
     ನಡೆದ
    0.24
    㓩
    0.24
    濱
    0.22
    㕶
    0.22
    annes
    0.21
    䢔
    0.21
    堰
    0.21
    )+"
    0.21
     తి
    0.21
    POSITIVE LOGITS
     dónde
    0.24
     donde
    0.23
     compens
    0.23
    gain
    0.23
     Compens
    0.23
     nadie
    0.22
     कोई
    0.22
    ₦
    0.22
     sangue
    0.22
     mejoras
    0.22
    Activations Density 0.027%

    No Known Activations