© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8073
    Prev
    Next
    INDEX
    Explanations

    sexual characteristics, role, reason, privilege

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    та
    0.51
    yki
    0.50
    вку
    0.50
    y
    0.49
     oth
    0.48
     exhaustive
    0.46
     DQN
    0.46
    ﻱ
    0.46
     WTO
    0.45
     ine
    0.44
    POSITIVE LOGITS
    }$
    0.52
    th
    0.49
     यानी
    0.46
     incluso
    0.46
    Translatef
    0.44
    のは
    0.43
    ษ
    0.43
    }$,
    0.42
    nect
    0.42
    navigationItem
    0.42
    Activations Density 0.332%

    No Known Activations