© 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. 18240
    Prev
    Next
    INDEX
    Explanations

    illegal substance synthesis

    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
    人用
    0.40
    dDevice
    0.38
    NewLabel
    0.37
    Prompt
    0.37
     Prand
    0.37
    貳
    0.37
     됩니다
    0.36
     prompt
    0.35
     personne
    0.35
     IndexError
    0.35
    POSITIVE LOGITS
    holes
    0.44
     Где
    0.41
     lakes
    0.40
    டக்கலை
    0.37
     Profes
    0.37
     സമ്പ
    0.37
     fires
    0.37
    ynthesis
    0.36
    helm
    0.36
    ਠ
    0.36
    Activations Density 0.062%

    No Known Activations