INDEX

Explanations

phrases indicating possibility or rules

oai_token-act-pair · gemini-2.0-flash

is

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

Datuak

-0.99

Personendaten

-0.95

 Réponses

-0.93

RenderAtEndOf

-0.90

出版年

-0.89

enderror

-0.88

Попис

-0.88

Portale

-0.87

Rhestr

-0.86

PreferredItem

-0.85

POSITIVE LOGITS

dup

0.45

ika

0.45

lik

0.43

↵↵↵

0.42

ole

0.40

وم

0.40

era

0.40

>&

0.40

exp

0.40

 there

0.39

Activations Density 0.646%

phrases indicating possibility or rules

is

No Comments

No Known Activations