INDEX

Explanations

code, file formats, and programming terms

oai_token-act-pair · gemini-2.0-flash

file reading/loading

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

ventus

-0.54

ⓧ

-0.52

ércio

-0.52

ût

-0.47

terness

-0.46

 Monfieur

-0.44

 Bedi

-0.44

]$}

-0.44

Langkah

-0.42

 anfitrión

-0.42

POSITIVE LOGITS

 initComponents

0.77

mobileqq

0.69

ftagPool

0.64

MigrationBuilder

0.63

EndInit

0.60

+#+#

0.55

IsContent

0.54

ThroughAttribute

0.54

rungsseite

0.53

evos

0.53

Activations Density 49.623%

code, file formats, and programming terms

file reading/loading

No Comments

No Known Activations