INDEX

Explanations

what appears to be partial or abbreviated words

oai_token-act-pair · gemini-2.0-flash

random text snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-2.61

aah

-1.02

aed

-0.94

aia

-0.94

aA

-0.91

ahi

-0.90

aing

-0.90

aR

-0.90

aas

-0.86

ا

-0.84

POSITIVE LOGITS

ostante

0.68

вної

0.44

ълга

0.44

CDATA

0.43

Cuánt

0.43

 isang

0.42

querySelector

0.41

tioners

0.41

dce

0.40

 sebuah

0.40

Activations Density 3.468%

what appears to be partial or abbreviated words

random text snippets

No Comments

No Known Activations