© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155331
    Prev
    Next
    INDEX
    Explanations

    qualities/states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ある
    0.41
    таў
    0.39
     Maynard
    0.37
    <unused2188>
    0.36
    sType
    0.36
    ティング
    0.35
     المتحدة
    0.35
    UMENTS
    0.35
     tingkat
    0.33
     ம
    0.33
    POSITIVE LOGITS
     inline
    0.49
     strait
    0.47
     acc
    0.47
     thought
    0.44
     whit
    0.44
     wh
    0.43
     thru
    0.42
     Thought
    0.42
    Thought
    0.40
     overwrite
    0.40
    Activations Density 0.003%

    No Known Activations