© 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. 15924
    Prev
    Next
    INDEX
    Explanations

    articles like 'a' followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    learning a lot

    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
    <bos>
    -0.59
    esez
    -0.57
    fromnode
    -0.52
     and
    -0.49
    }`).
    -0.49
    ngrx
    -0.47
    UrlResolution
    -0.46
    šinou
    -0.46
    CodeAttribute
    -0.46
     &
    -0.44
    POSITIVE LOGITS
     Riproduzione
    0.61
     ſtate
    0.60
     الحره
    0.59
     ſeveral
    0.59
     ſtand
    0.59
     ſhould
    0.58
     purpoſe
    0.58
     quæ
    0.56
    amerikanischer
    0.54
     ſt
    0.53
    Activations Density 6.573%

    No Known Activations