© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3068
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of someone's performance or actions

    oai_token-act-pair · gemini-2.0-flash

    a/an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    oredCriteria
    -0.96
    astéroïdes
    -0.91
    writeField
    -0.90
    httphttps
    -0.88
     utafitiHapana
    -0.82
    webElementXpaths
    -0.80
    клопе
    -0.77
     GenerationType
    -0.77
    tadır
    -0.74
    WithIOException
    -0.74
    POSITIVE LOGITS
     an
    0.53
    An
    0.46
     đầu
    0.40
    Tikang
    0.39
     An
    0.39
    Clik
    0.38
     innings
    0.36
     الاطلاع
    0.35
    FromArgb
    0.34
     ad
    0.34
    Activations Density 2.319%

    No Known Activations