© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12195
    Prev
    Next
    INDEX
    Explanations

    something that is either Italian language or medical terminology or related to legal documents.

    oai_token-act-pair · gemini-2.0-flash

    ache

    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
    bootstrapcdn
    -0.74
    KommentareTeilen
    -0.70
    SourceChecksum
    -0.67
    IntoConstraints
    -0.66
     bezeichneter
    -0.64
    httphttps
    -0.57
     resourceCulture
    -0.54
    OpenHelper
    -0.52
    .*")]
    -0.52
     Chwiliwch
    -0.52
    POSITIVE LOGITS
    mmate
    0.56
     agricole
    0.53
    creative
    0.51
     diffuse
    0.51
    ///</
    0.50
    ')}}"
    0.50
     ferme
    0.50
     integrative
    0.50
    icate
    0.50
    uose
    0.48
    Activations Density 1.545%

    No Known Activations