© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61337
    Prev
    Next
    INDEX
    Explanations

    looking forward to

    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_11_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
     የሆነ
    0.36
     Фурга
    0.36
    робнее
    0.36
     femminile
    0.36
     royaume
    0.34
     אר
    0.34
    オ
    0.33
     sirop
    0.33
    間に
    0.32
     returnValue
    0.32
    POSITIVE LOGITS
    m
    0.40
    <0xA0>
    0.39
    ai
    0.39
    \
    0.38
    t
    0.37
    ong
    0.36
     notor
    0.35
     m
    0.35
    aw
    0.34
    idimensional
    0.34
    Activations Density 0.004%

    No Known Activations