© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and gerunds used in the context of celebrations and events

    oai_token-act-pair · gemini-2.0-flash

    celebrations and relationships

    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
    PickerController
    -0.84
     الحره
    -0.82
    Билгалдахарш
    -0.71
     محفوظة
    -0.67
     وتسجيلات
    -0.65
    IntoConstraints
    -0.65
    脚注の使い方
    -0.63
    EndGlobalSection
    -0.63
    Portail
    -0.61
     Процитовано
    -0.61
    POSITIVE LOGITS
    :]:
    0.58
     engagement
    0.52
     prom
    0.52
    kheim
    0.51
    OON
    0.48
    UnknownFieldSet
    0.46
    nikon
    0.46
    :])
    0.45
    "}\
    0.44
    ukah
    0.44
    Activations Density 0.532%

    No Known Activations