INDEX

Explanations

the word "punch" or related words

oai_token-act-pair · gemini-2.0-flash

punch

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

Not in Any Lists

No Comments

Negative Logits

 confronti

-0.49

WAUKEE

-0.46

monių

-0.46

 dàng

-0.45

 calculées

-0.44

 wystaw

-0.44

 dolayı

-0.43

Comté

-0.43

 Nearly

-0.43

 disparu

-0.42

POSITIVE LOGITS

MigrationBuilder

0.82

клопе

0.68

tagHelperRunner

0.62

posedge

0.58

brainly

0.58

providedIn

0.57

 المعيارى

0.57

uality

0.56

onAttach

0.56

ParallelGroup

0.55

Activations Density 0.757%

the word "punch" or related words

punch

No Comments

No Known Activations