© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17960
    Prev
    Next
    INDEX
    Explanations

    talking or conversation

    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
    ന്നും
    0.38
    WhiteElo
    0.38
    芜
    0.37
    GRESS
    0.37
     Fall
    0.36
    immä
    0.35
    묘
    0.35
     Innoc
    0.34
    톨
    0.34
     Na
    0.34
    POSITIVE LOGITS
     conversar
    1.04
    Talk
    1.02
     talk
    1.01
    talk
    0.98
     Talk
    0.97
     talks
    0.96
     talking
    0.95
     conversa
    0.92
    Conversation
    0.91
     talked
    0.91
    Activations Density 0.175%

    No Known Activations