INDEX

Explanations

words and phrases relating to trains and safety

oai_token-act-pair · gemini-2.0-flash

traffic

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

and

-0.47

-0.43

-0.41

in

-0.41

-0.40

ul

-0.40

ab

-0.40

la

-0.39

POSITIVE LOGITS

AddTagHelper

1.24

reportWebVitals

1.19

Personensuche

1.16

parsedMessage

1.16

 createSlice

1.14

Искәрмәләр

1.12

 <<<<<<<<<<<<<<

1.10

ChildScrollView

1.10

########.

1.09

Efq

1.09

Activations Density 9.571%

words and phrases relating to trains and safety

traffic

No Comments

No Known Activations