© 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. 2677
    Prev
    Next
    INDEX
    Explanations

    occurrences of the words "in", "thing", "built", "wasn", "don", "what", "this", "saudi", and "belonged".

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    ");
    -0.54
    /");
    -0.53
    ']);
    -0.52
    "):
    -0.48
    /",
    -0.48
    ValueStyle
    -0.48
     AssemblyCulture
    -0.48
    verwijspagina
    -0.47
    ");
    -0.47
     estekak
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.75
     مُعرِّف
    0.71
     صوتيه
    0.69
     Theſe
    0.68
     يتيمه
    0.66
     fevere
    0.62
     pinulongan
    0.62
     Monfieur
    0.61
     pleaſure
    0.61
     ſeveral
    0.60
    Activations Density 9.857%

    No Known Activations