INDEX

Explanations

words related to various types of insects, worms, shells or similar creatures

oai_token-act-pair · gemini-2.0-flash

species

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Dict

-0.47

up

-0.41

aid

-0.40

教

-0.40

 back

-0.40

 ward

-0.40

Hos

-0.39

Jer

-0.39

фон

-0.38

tvrt

-0.38

POSITIVE LOGITS

Datuak

1.08

 Roskov

0.77

 insect

0.74

 Insects

0.73

RTEE

0.72

insect

0.71

 Insect

0.71

__":

0.69

 Entomol

0.69

 виправивши

0.67

Activations Density 0.425%

words related to various types of insects, worms, shells or similar creatures

species

No Comments

No Known Activations