© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6677
    Prev
    Next
    INDEX
    Explanations

    text expressing opinions, beliefs, or advice, often using words associated with thinking, learning, or teaching.

    oai_token-act-pair · gemini-2.0-flash

    Diverse topics and writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Úl
    -0.51
     nuages
    -0.46
    refundable
    -0.44
    sidemargin
    -0.43
    spaghetti
    -0.43
    *********/
    -0.42
     storia
    -0.41
     dodat
    -0.41
    Maf
    -0.40
     scolaires
    -0.40
    POSITIVE LOGITS
    UpdateCommand
    0.70
     CreateTagHelper
    0.66
    sterdam
    0.65
     digress
    0.63
     Wikimédia
    0.62
    rosoft
    0.59
     INTERESAR
    0.58
    migrationBuilder
    0.57
    BeginInit
    0.56
    DeleteCommand
    0.56
    Activations Density 2.251%

    No Known Activations