© 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. 11976
    Prev
    Next
    INDEX
    Explanations

    code-related syntax, like braces, numbers, or imports

    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
     kysy
    -0.60
     enfans
    -0.59
     scheda
    -0.59
     henkil
    -0.59
     tarko
    -0.58
     démocr
    -0.56
    izante
    -0.56
     détect
    -0.56
     dieux
    -0.56
     présidenti
    -0.56
    POSITIVE LOGITS
    ########.
    0.56
    intios
    0.48
     restaura
    0.48
    tanleria
    0.47
    tvguidetime
    0.46
     Nauk
    0.46
    lastIndexOf
    0.45
    sidemargin
    0.45
    "%(
    0.45
     distanciation
    0.45
    Activations Density 24.421%

    No Known Activations