© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7598
    Prev
    Next
    INDEX
    Explanations

    the prefix "pre"

    oai_token-act-pair · gemini-2.0-flash

    pre

    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
     preload
    -0.45
    ंदीखरीदारी
    -0.42
    Rujuakan
    -0.41
    utilisons
    -0.40
    turnstile
    -0.40
     $=-
    -0.39
     invokingState
    -0.39
    הערות
    -0.38
    లాలు
    -0.38
    ########.
    -0.37
    POSITIVE LOGITS
     فريبيس
    0.65
    nean
    0.62
    gouv
    0.59
    música
    0.58
    nons
    0.58
    nace
    0.57
    hibits
    0.57
    pheres
    0.56
    GORITH
    0.56
    banners
    0.56
    Activations Density 3.768%

    No Known Activations