INDEX

Explanations

percentages, numerical data, and references to tables

oai_token-act-pair · gemini-2.0-flash

percentages and statistics

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

core

-0.51

-0.50

-0.48

 narci

-0.48

olle

-0.42

le

-0.42

ría

-0.40

kwij

-0.39

eb

-0.39

 çiz

-0.39

POSITIVE LOGITS

GOTREF

0.91

 ThemeData

0.90

:✨

0.89

pausal

0.82

InstrumentedTest

0.82

StructEnd

0.81

########.

0.81

INCREF

0.78

енча

0.77

AsUp

0.76

Activations Density 1.862%

percentages, numerical data, and references to tables

percentages and statistics

No Comments

No Known Activations