© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81915
    Prev
    Next
    INDEX
    Explanations

    reputational damage

    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_53_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
    彡
    0.48
     względu
    0.40
    rugu
    0.38
    མ་
    0.37
    letzt
    0.36
    renched
    0.36
    rypt
    0.35
    렇게
    0.35
    ached
    0.34
     명
    0.33
    POSITIVE LOGITS
    ా
    0.91
    ે
    0.87
    িও
    0.86
    ি
    0.80
    ு
    0.75
    aa
    0.74
    ು
    0.72
    ações
    0.72
    ాన్ని
    0.71
    ał
    0.71
    Activations Density 0.004%

    No Known Activations