© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89842
    Prev
    Next
    INDEX
    Explanations

    harmful or unethical content

    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_11_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
    as
    0.72
    to
    0.65
    beta
    0.64
    regulatory
    0.61
    gos
    0.61
    ﻟ
    0.60
    ﻠ
    0.59
    लिस
    0.59
    3
    0.58
    burning
    0.58
    POSITIVE LOGITS
    ีด
    0.59
    ี
    0.58
    їв
    0.56
    ius
    0.56
     saurait
    0.55
    ين
    0.55
    iert
    0.53
     $=$
    0.53
     Judo
    0.53
     WAV
    0.52
    Activations Density 0.014%

    No Known Activations