INDEX

Explanations

words and phrases related to health, support, standards, measurements, and changes.

oai_token-act-pair · gemini-2.0-flash

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 szól

-0.45

 precisione

-0.44

Ђ

-0.43

 missione

-0.42

 suffit

-0.42

rand

-0.42

 olvas

-0.41

 plomo

-0.40

 ayudado

-0.40

 particuliers

-0.40

POSITIVE LOGITS

StoryboardSegue

0.96

tagext

0.79

MemoryWarning

0.75

migrationBuilder

0.75

jspx

0.75

AndEndTag

0.74

 ExecuteAsync

0.71

 continúas

0.71

RegressionTest

0.68

OrNil

0.68

Activations Density 3.976%

words and phrases related to health, support, standards, measurements, and changes.

and

No Known Activations