INDEX

Explanations

phrases that quantify or describe the quantity of something

oai_token-act-pair · gemini-2.0-flash

all

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

Personensuche

-0.55

<bos>

-0.54

SBATCH

-0.53

’

-0.47

まで

-0.46

-0.42

ik

-0.41

 eingesch

-0.40

े

-0.40

ेश

-0.39

POSITIVE LOGITS

AutoScale

0.90

 виправивши

0.89

addContainerGap

0.77

NUMX

0.71

 يتيمه

0.71

$_"

0.70

RegressionTest

0.68

]--;

0.66

 متعلقه

0.65

ftagPool

0.65

Activations Density 1.431%

phrases that quantify or describe the quantity of something

all

No Comments

No Known Activations