© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11943
    Prev
    Next
    INDEX
    Explanations

    positive statements about product features, sometimes interspersed with more general emotion-related terms.

    oai_token-act-pair · gemini-2.0-flash

    technical terms with 'you' and 'feeling'

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

    feel

    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
     بيها
    -0.67
    gdx
    -0.67
    RequestParam
    -0.64
    __(/*!
    -0.63
     MonoBehaviour
    -0.62
    رشف
    -0.60
     GenerationType
    -0.60
    IntoConstraints
    -0.59
    mybatisplus
    -0.59
     nakalista
    -0.58
    POSITIVE LOGITS
    usercontent
    0.48
     ergo
    0.47
    ITOR
    0.47
     Ergo
    0.47
     összes
    0.46
    cionales
    0.44
    itor
    0.44
    BufferException
    0.42
    PhysRev
    0.41
     baratas
    0.41
    Activations Density 0.336%

    No Known Activations