© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201855
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
     firefighting
    0.38
    ្យ
    0.38
     PLIST
    0.38
     gia
    0.37
    ➹
    0.37
     block
    0.36
     পু
    0.36
     weren
    0.36
     Profile
    0.36
     porcine
    0.36
    POSITIVE LOGITS
    key
    0.41
    Bob
    0.40
    keys
    0.40
    വേഷ
    0.40
     рит
    0.38
    keyCode
    0.38
    bob
    0.38
    鬨
    0.38
     rhyth
    0.37
    cym
    0.37
    Activations Density 0.000%

    No Known Activations