INDEX

Explanations

words that are relevant to politics and governance

oai_token-act-pair · gemini-2.0-flash

government/political news

np_max-act · gemini-2.0-flash

New Auto-Interp

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

Архівовано

-0.60

-0.57

 hope

-0.53

 στε

-0.53

 חיצוניים

-0.52

 ramach

-0.50

 hopes

-0.50

 Ride

-0.50

kian

-0.49

EndInit

-0.49

POSITIVE LOGITS

BufferException

0.73

 '\\;'

0.72

 mergeFrom

0.71

 nakalista

0.70

 biometric

0.67

yntaxException

0.64

UnusedPrivate

0.64

SPATH

0.63

scribers

0.59

 interruptions

0.58

Activations Density 2.930%

words that are relevant to politics and governance

government/political news

No Comments

No Known Activations

words that are relevant to politics and governance

government/political news

No Comments

No Known Activations