© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ರಿಸ
    0.37
    ților
    0.36
    urer
    0.34
    ewel
    0.34
     השי
    0.34
    vm
    0.33
    ivr
    0.33
    래
    0.33
    ώ
    0.33
     czasu
    0.32
    POSITIVE LOGITS
     steam
    0.38
    feldt
    0.38
     lubricating
    0.37
     equipment
    0.37
     aide
    0.37
    のために
    0.36
    }}=(
    0.36
     shave
    0.35
    joy
    0.35
     sucht
    0.35
    Activations Density 0.000%

    No Known Activations