INDEX

Explanations

phrases related to movie credits

oai_token-act-pair · gemini-2.0-flash

films and books

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 CanadaChoose

-0.99

ResponseWriter

-0.87

parsedMessage

-0.85

 protoimpl

-0.84

WillAppear

-0.83

msgTypes

-0.82

 Roskov

-0.82

 Савезне

-0.79

 HasFactory

-0.79

tonsoft

-0.78

POSITIVE LOGITS

0.44

"}

0.43

 Tere

0.41

ยัง

0.40

 profesionales

0.40

官

0.39

 Deva

0.39

[:]

0.39

 carrés

0.39

'):

0.38

Activations Density 1.637%

phrases related to movie credits

films and books

No Comments

No Known Activations