INDEX

Explanations

items relevant to numbered or bulleted lists

oai_token-act-pair · gemini-2.0-flash

code-related tokens

np_token-act-pair-logits · gemini-2.0-flash

Nursing and medicine texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

DoubleQuotes

-0.54

 كومونز

-0.50

 Numerology

-0.47

hazi

-0.46

 سكانية

-0.45

//-->

-0.42

nocześnie

-0.42

oroz

-0.41

 برانيه

-0.41

MessageTagHelper

-0.41

POSITIVE LOGITS

AnimationsModule

0.77

MetaObject

0.62

Personendaten

0.61

)++;

0.59

PerformLayout

0.57

rungsseite

0.55

WireFormatLite

0.54

 &___

0.54

yyj

0.53

ontological

0.53

Activations Density 1.765%

items relevant to numbered or bulleted lists

code-related tokens

Nursing and medicine texts

No Comments

No Known Activations