© 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. 16309
    Prev
    Next
    INDEX
    Explanations

    code snippets with indentations

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     itſelf
    -0.47
    !")
    -0.40
     Efq
    -0.37
    <bos>
    -0.36
    leſs
    -0.35
    .")
    -0.35
     }}$}
    -0.34
    ſelves
    -0.34
    .",
    -0.34
    POSITIVE LOGITS
     CanadaChoose
    0.88
     Madsen
    0.86
    #+#
    0.86
    fromnode
    0.85
     setuptools
    0.85
    CppCodeGen
    0.84
     estekak
    0.84
    Geplaatst
    0.83
    Personensuche
    0.83
     Baumann
    0.82
    Activations Density 2.224%

    No Known Activations