© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4177
    Prev
    Next
    INDEX
    Explanations

    the topic of hemp and cannabis

    oai_token-act-pair · gemini-2.0-flash

    full, plus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CBD
    -0.87
    CBD
    -0.83
     leaſt
    -0.79
     cbd
    -0.79
     Cbd
    -0.73
     miſ
    -0.68
     Reſ
    -0.68
     firſt
    -0.66
    NUMX
    -0.65
     aſſ
    -0.65
    POSITIVE LOGITS
     Full
    0.71
     full
    0.68
    Full
    0.67
     plus
    0.63
     Plus
    0.61
    plus
    0.60
    Plus
    0.56
     pura
    0.56
     pure
    0.55
    full
    0.52
    Activations Density 0.801%

    No Known Activations