© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 64
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_12_width_16k_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
    onka
    0.35
    成分
    0.35
    )$:
    0.33
    ochlor
    0.33
     septic
    0.32
    enie
    0.32
     राणा
    0.31
     primeira
    0.31
    etu
    0.31
    เ
    0.31
    POSITIVE LOGITS
     intolerable
    0.36
     welcher
    0.35
     tolerable
    0.34
     Astronomy
    0.33
     excruciating
    0.33
     VEL
    0.32
     relativistic
    0.32
     radiates
    0.32
     traverse
    0.31
     welchem
    0.31
    Activations Density 0.006%

    No Known Activations