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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13186
    Prev
    Next
    INDEX
    Explanations

    text related to image processing and display, or to manipulating technology.

    oai_token-act-pair · gemini-2.0-flash

    Digital media

    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
    cagon
    -0.59
    牲
    -0.47
    providedIn
    -0.47
    bollah
    -0.47
    awtextra
    -0.45
     ofs
    -0.45
    fuzz
    -0.45
    assment
    -0.45
    psum
    -0.45
    penes
    -0.44
    POSITIVE LOGITS
    EndProject
    0.59
    SupportActionBar
    0.58
    isielt
    0.56
     restTemplate
    0.55
     jadx
    0.54
    getRuntime
    0.54
     Bewußt
    0.53
     Voulez
    0.53
    importe
    0.52
     UIImage
    0.51
    Activations Density 15.575%

    No Known Activations