© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64939
    Prev
    Next
    INDEX
    Explanations

    YouTube subscribers

    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_41_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
     पिछड़ा
    0.46
     semif
    0.43
     slä
    0.40
     पिछड़े
    0.40
     acumin
    0.37
     semia
    0.37
    偶
    0.37
    Replacement
    0.36
     odstr
    0.36
    团
    0.36
    POSITIVE LOGITS
     subscription
    2.88
     subscribe
    2.84
     subscribed
    2.80
     subscriptions
    2.75
     subscribing
    2.63
     Subscription
    2.59
     subscrib
    2.53
    subscribe
    2.50
     Subscribe
    2.48
    Subscription
    2.48
    Activations Density 0.005%

    No Known Activations