© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15886
    Prev
    Next
    INDEX
    Explanations

    legal and academic language (views, institutes, health, funding, supported, research, scientist, award, article, authors)

    oai_token-act-pair · gemini-2.0-flash

    Disclaimers and statements of non-responsibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     '\\;'
    -0.51
    ]));
    -0.49
     jump
    -0.49
    ')));
    -0.49
     Jump
    -0.48
    Portale
    -0.48
    ")));
    -0.48
    GEBURTSDATUM
    -0.47
    بوابة
    -0.46
    tangentMode
    -0.46
    POSITIVE LOGITS
     facie
    0.55
     paroi
    0.55
     prejudicial
    0.54
     solicited
    0.54
     ejus
    0.54
     prescri
    0.54
     enforceable
    0.53
     unduly
    0.52
    conditioned
    0.52
     thal
    0.52
    Activations Density 9.800%

    No Known Activations