© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176189
    Prev
    Next
    INDEX
    Explanations

    code after `const` or `function`

    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_20_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
     kidneys
    0.41
     p
    0.39
     siap
    0.39
     cuando
    0.38
     KSI
    0.37
     आणखी
    0.37
    —
    0.36
     (%
    0.36
     verantwortlich
    0.36
     сколько
    0.36
    POSITIVE LOGITS
    Ⅽ
    0.43
    ехала
    0.40
    Opin
    0.39
    езде
    0.39
    RationalValue
    0.38
    已
    0.37
    琕
    0.37
     تاکہ
    0.36
     तौर
    0.36
    ThemeProvider
    0.36
    Activations Density 0.000%

    No Known Activations