INDEX

Explanations

text related to machine learning training processes and data analysis

oai_token-act-pair · gemini-2.0-flash

training

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

 IndexPath

-0.53

principalTable

-0.47

 inhibition

-0.47

Geplaatst

-0.47

monials

-0.47

oltán

-0.46

NewReader

-0.46

 réessayer

-0.46

Tried

-0.46

bobox

-0.44

POSITIVE LOGITS

AnchorStyles

0.65

Suara

0.65

 obiec

0.63

 يتيمه

0.60

AutoScaleMode

0.60

ⓘ

0.59

WindowConstants

0.59

 bakgrund

0.58

study

0.58

getMenuInflater

0.56

Activations Density 1.647%

text related to machine learning training processes and data analysis

training

No Comments

No Known Activations