© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35319
    Prev
    Next
    INDEX
    Explanations

    access to resources, opportunity, housing

    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_31_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
    創新
    0.36
    ?<
    0.36
    শ্ম
    0.35
    caling
    0.35
    !<
    0.34
     siglas
    0.33
    }<
    0.33
    Npm
    0.33
    ffiche
    0.32
    !)
    0.32
    POSITIVE LOGITS
    vertices
    0.40
    Legal
    0.39
     housing
    0.38
     legal
    0.38
     Legal
    0.36
    ቀር
    0.36
     Housing
    0.35
     ಎರಡ
    0.35
     ج
    0.35
     lawyers
    0.35
    Activations Density 0.021%

    No Known Activations