© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3461
    Prev
    Next
    INDEX
    Explanations

    positive/encouraging words and action verbs

    oai_token-act-pair · gemini-2.0-flash

    experiences

    np_max-act · gemini-2.0-flash

    capitalized words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IntoConstraints
    -1.23
    parsedMessage
    -1.00
    rungsseite
    -0.96
     المعيارى
    -0.94
     Equipped
    -0.94
     Riproduzione
    -0.93
    HostException
    -0.93
    MockBean
    -0.93
     Played
    -0.93
    ConstraintMaker
    -0.92
    POSITIVE LOGITS
    larak
    0.53
    Rule
    0.47
    Error
    0.47
     living
    0.45
    мени
    0.45
     care
    0.44
     Rule
    0.44
    Corollary
    0.44
     vibrant
    0.44
     Chart
    0.43
    Activations Density 5.009%

    No Known Activations