INDEX

Explanations

numerical data, especially data ranges and negative numbers

oai_token-act-pair · gemini-2.0-flash

mathematical symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

</thead>

-0.55

Хро

-0.54

SerializedSize

-0.54

:]:

-0.53

cry

-0.51

IConfiguration

-0.50

Trama

-0.49

 تخ

-0.49

SequentialGroup

-0.48

 resourceCulture

-0.48

POSITIVE LOGITS

ształ

0.56

strand

0.56

 TextInputType

0.54

SuppressLint

0.54

ganj

0.53

Buildable

0.52

opar

0.51

τεί

0.49

 Vereinig

0.49

PackageManager

0.48

Activations Density 0.641%

numerical data, especially data ranges and negative numbers

mathematical symbols

No Comments

No Known Activations