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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9144
    Prev
    Next
    INDEX
    Explanations

    words related to both graphic sexual acts and emotional distress

    oai_token-act-pair · gemini-2.0-flash

    sounds and expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IsMutable
    -0.59
    closedir
    -0.54
     typelib
    -0.50
     verticales
    -0.48
    JspWriter
    -0.45
    Laser
    -0.45
     ActiveRecord
    -0.44
     Remind
    -0.44
    UnsafeEnabled
    -0.44
     alarme
    -0.43
    POSITIVE LOGITS
    }{*}{}
    0.72
    featureID
    0.68
    }{*}{
    0.65
     ujednoznacz
    0.65
     considérons
    0.59
    enumerate
    0.58
    ReusableCell
    0.56
    ̸
    0.56
    Izvori
    0.55
    Bakgrunnsstoff
    0.54
    Activations Density 17.496%

    No Known Activations