INDEX

Explanations

references to New York

oai_token-act-pair · gemini-2.0-flash

New York City

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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



-0.75

Lähteet

-0.69

complexContent

-0.66

 légales

-0.66

 defaultstate

-0.63

oredCriteria

-0.63

brainly

-0.62

Aiheesta

-0.61

Билгалдахарш

-0.58

cotch

-0.56

POSITIVE LOGITS

 Manhattan

1.09

NYC

0.97

NY

0.96

Manhattan

0.94

NY

0.93

NYC

0.90

 NYPD

0.88

 Bronx

0.82

New

0.79

🗽

0.77

Activations Density 0.518%

references to New York

New York City

No Comments

No Known Activations