© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169199
    Prev
    Next
    INDEX
    Explanations

    can

    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_56_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
     honestly
    0.51
     legitimately
    0.37
     ונ
    0.36
    濑
    0.36
    ncies
    0.35
    stressed
    0.35
    étant
    0.35
     Canton
    0.35
    altering
    0.35
    ᴵ
    0.35
    POSITIVE LOGITS
     be
    0.59
     Process
    0.56
     process
    0.55
    process
    0.50
     lay
    0.47
     roam
    0.47
     close
    0.46
     walk
    0.44
    Process
    0.44
    :',
    0.44
    Activations Density 0.003%

    No Known Activations