© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8605
    Prev
    Next
    INDEX
    Explanations

    phrases including "fellow" and relationship words like "other," "kill," and "we"

    oai_token-act-pair · gemini-2.0-flash

    humans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MLLoader
    -0.76
     Sociale
    -0.68
    SequentialGroup
    -0.65
     pharynx
    -0.65
     vocale
    -0.65
    OrNil
    -0.64
     kaynağından
    -0.63
     NUKAT
    -0.63
    ėms
    -0.63
     оригіналу
    -0.63
    POSITIVE LOGITS
     human
    0.81
     humans
    0.69
    human
    0.56
     Human
    0.53
    Humans
    0.51
     Muslim
    0.50
     Muslims
    0.50
     hu
    0.50
     Christians
    0.50
     Man
    0.50
    Activations Density 1.522%

    No Known Activations