INDEX

Explanations

words or phrases related to formal discussions, reports, or research

oai_token-act-pair · gemini-2.0-flash

replacements, representations, claims

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.79

انيف

-0.63

 ſeveral

-0.63

Portail

-0.63

 fieldNum

-0.62

 ſever

-0.60

 незавершена

-0.60

abestanden

-0.59

 Signalez

-0.58

 reaſon

-0.58

POSITIVE LOGITS

rungsseite

0.62

pley

0.46

poto

0.46

 "..\..\

0.44

 ComVisible

0.43

^{+}\

0.42

 beleza

0.42

himo

0.42

ylus

0.42

 cadáver

0.42

Activations Density 75.161%

words or phrases related to formal discussions, reports, or research

replacements, representations, claims

No Comments

No Known Activations