© 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
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15031
    Prev
    Next
    INDEX
    Explanations

    sentences describing faint surrounding noises being heard by a character or person

    oai_token-act-pair · gemini-2.0-flash

    Sound detection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     للاسماء
    -0.79
     utafitiHapana
    -0.71
     '\\;'
    -0.64
     فريبيس
    -0.59
    EFIAPI
    -0.59
    قایناق‌لار
    -0.59
     стаття
    -0.58
     beginnetje
    -0.57
    ttemberg
    -0.57
    AndEndTag
    -0.54
    POSITIVE LOGITS
    ragment
    0.53
     SwitchCompat
    0.52
    ities
    0.52
    TimePicker
    0.52
     tapping
    0.52
    Personendaten
    0.51
     lachen
    0.50
    idin
    0.50
     Stimme
    0.49
     TAP
    0.47
    Activations Density 3.933%

    No Known Activations