© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14597
    Prev
    Next
    INDEX
    Explanations

    code snippets containing symbols, functions, and variable assignments

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    =
    -1.38
    ={
    -1.18
    ='
    -1.09
    ="
    -1.06
    –
    -1.05
    -"
    -1.05
    +
    -1.04
    —
    -1.04
    —"
    -1.02
    =”
    -1.01
    POSITIVE LOGITS
     JADX
    0.50
    orteur
    0.48
    Ỏ
    0.47
    lottes
    0.47
     eser
    0.46
     aveug
    0.46
     présidenti
    0.45
    [toxicity=0]
    0.44
     iconFacebook
    0.44
    tapkan
    0.44
    Activations Density 8.587%

    No Known Activations