© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16106
    Prev
    Next
    INDEX
    Explanations

    conversational English, especially related to personal opinions or experiences

    oai_token-act-pair · gemini-2.0-flash

    About people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    forChild
    -0.58
    Chham
    -0.56
     hozz
    -0.51
    IVEREF
    -0.50
    IATION
    -0.50
    PONSE
    -0.50
    ποίη
    -0.49
    كونات
    -0.48
    omorphology
    -0.48
    actylus
    -0.48
    POSITIVE LOGITS
     who
    0.64
     Roskov
    0.63
    LabelTagHelper
    0.61
    Aktualisiert
    0.60
    SourceChecksum
    0.58
    tvguidetime
    0.57
     faking
    0.57
    itieren
    0.57
     BoxDecoration
    0.55
     myſelf
    0.55
    Activations Density 4.435%

    No Known Activations