© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6178
    Prev
    Next
    INDEX
    Explanations

    code syntax

    oai_token-act-pair · gemini-2.0-flash

    non-ASCII character strings

    np_token-act-pair-logits · gpt-4o-mini

    Code, foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     nakalista
    -0.85
    Portail
    -0.81
    ImageContext
    -0.68
     Portail
    -0.65
     AssemblyProduct
    -0.64
     misschien
    -0.63
    PMailer
    -0.63
     дописавши
    -0.63
    Portale
    -0.60
    PropertyGroup
    -0.60
    POSITIVE LOGITS
     المعيارى
    0.42
    綜合報導
    0.41
    Rendering
    0.40
    gente
    0.40
    InBackground
    0.40
    stdc
    0.40
    opsida
    0.40
     aj
    0.39
    anthene
    0.39
     manqué
    0.38
    Activations Density 0.101%

    No Known Activations