© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205200
    Prev
    Next
    INDEX
    Explanations

    names or people

    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_46_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
     tecnico
    0.38
    訳
    0.36
    ointment
    0.36
    ILIO
    0.35
    шої
    0.34
    ếp
    0.34
    Arithmetic
    0.34
    psilon
    0.34
    ville
    0.34
    sigmaf
    0.34
    POSITIVE LOGITS
     சுதந்திர
    0.46
    澹
    0.40
     Norman
    0.40
     Proper
    0.38
     neglects
    0.38
     Flora
    0.38
     proper
    0.38
     Kingdom
    0.38
     MPG
    0.38
     Hallmark
    0.38
    Activations Density 0.000%

    No Known Activations