INDEX

Explanations

first-person pronouns and related language reflecting a personal narrative

oai_token-act-pair · gemini-2.0-flash

foreign words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

chyma

-0.50

حياتها

-0.46

MessageTagHelper

-0.44

 consultato

-0.44

AnimationsModule

-0.42

UniformLocation

-0.41

XtraGrid

-0.41

furl

-0.40

gamot

-0.39

OK

-0.39

POSITIVE LOGITS

tanleria

0.68

 صوتيه

0.66

TintMode

0.65

فایل‌لار

0.65

 potenza

0.65

 sabbia

0.62

power

0.59

migrationBuilder

0.59

 OFDb

0.58

ixante

0.58

Activations Density 3.105%

first-person pronouns and related language reflecting a personal narrative

foreign words

No Comments

No Known Activations