© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 995
    Prev
    Next
    INDEX
    Explanations

    mentions of suspension, ropes, or hanging

    oai_token-act-pair · gemini-2.0-flash

    hang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    complexType
    -0.59
     bParam
    -0.54
    alsch
    -0.53
    JsonHelper
    -0.52
     Testa
    -0.52
    rån
    -0.52
    toHaveBeen
    -0.51
     destroyer
    -0.50
    pielt
    -0.50
    Risultati
    -0.49
    POSITIVE LOGITS
    '}),
    0.66
     suspendu
    0.64
    suspension
    0.64
    suspended
    0.60
     <>",
    0.57
     suspensions
    0.57
     móc
    0.57
     treo
    0.56
    suspend
    0.55
     }}$}
    0.55
    Activations Density 0.728%

    No Known Activations