© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16404
    Prev
    Next
    INDEX
    Explanations

    SQLAlchemy import

    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_34_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
    äden
    0.35
    ǁ
    0.34
    efi
    0.32
    Addresses
    0.30
    CCA
    0.30
     упра
    0.30
    Builder
    0.30
    ABA
    0.29
    黜
    0.29
     volum
    0.29
    POSITIVE LOGITS
    𝘖
    0.32
    ्ला
    0.31
     pož
    0.31
    Timelapse
    0.31
     Slovak
    0.30
     Welsh
    0.30
     drastic
    0.30
    แพ
    0.30
     girlfriend
    0.29
     zit
    0.29
    Activations Density 0.005%

    No Known Activations