INDEX

Explanations

code snippets and/or program configuration data including references to content, request and API calls.

oai_token-act-pair · gemini-2.0-flash

equals sign

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 MainAxisSize

-0.88

 surla

-0.82

SBATCH

-0.82

SequentialGroup

-0.77

KommentareTeilen

-0.77

AutoScaleMode

-0.77

UnusedPrivate

-0.71

 متعلقه

-0.68

 AssemblyVersion

-0.68

WithIOException

-0.67

POSITIVE LOGITS

def

0.48

"""

0.47

len

0.47

0.46

()):

0.45

ep

0.45

#)

0.43

“

0.43

0.42

print

0.41

Activations Density 9.683%

code snippets and/or program configuration data including references to content, request and API calls.

equals sign

No Comments

No Known Activations