© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    instances of articles combined with adjectives or nouns with negative connotations

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    }")
    
    -0.68
    ())))
    -0.67
     JpaRepository
    -0.66
    ])),
    -0.65
    expandindo
    -0.63
    ')));
    -0.62
    ()))
    
    -0.62
    ]))
    
    -0.60
    []):
    -0.60
    ])));
    -0.59
    POSITIVE LOGITS
     betweenstory
    0.47
     poffible
    0.44
    pisode
    0.44
    ocarpus
    0.43
    ABULARY
    0.43
    انون
    0.43
    anius
    0.42
    FRONT
    0.41
    front
    0.41
    angsaan
    0.41
    Activations Density 3.969%

    No Known Activations